{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "e3131552-f8fe-4ec4-b41b-5606274d44d8", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (4, 3)
stateyearpop
stri64f64
"Ohio"20001.5
"Ohio"20011.7
"Ohio"20023.6
"Nevada"20012.4
" ], "text/plain": [ "shape: (4, 3)\n", "┌────────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞════════╪══════╪═════╡\n", "│ Ohio ┆ 2000 ┆ 1.5 │\n", "│ Ohio ┆ 2001 ┆ 1.7 │\n", "│ Ohio ┆ 2002 ┆ 3.6 │\n", "│ Nevada ┆ 2001 ┆ 2.4 │\n", "└────────┴──────┴─────┘" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import polars as pl\n", "\n", "df = pl.DataFrame({'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada'],\n", " 'year': [2000, 2001, 2002, 2001],\n", " 'pop': [1.5, 1.7, 3.6, 2.4]})" ] }, { "cell_type": "code", "execution_count": 2, "id": "03eb5f7d-7e84-4607-9f31-9c6490165eaf", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
0Ohio20001.5
1Ohio20011.7
2Ohio20023.6
3Nevada20012.4
\n", "
" ], "text/plain": [ " state year pop\n", "0 Ohio 2000 1.5\n", "1 Ohio 2001 1.7\n", "2 Ohio 2002 3.6\n", "3 Nevada 2001 2.4" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "\n", "dfa = pd.DataFrame({'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada'],\n", " 'year': [2000, 2001, 2002, 2001],\n", " 'pop': [1.5, 1.7, 3.6, 2.4]})" ] }, { "cell_type": "code", "execution_count": 3, "id": "0ee87cc5-feb2-413d-a012-49e1e898c792", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
Ohio20023.6
Nevada20012.4
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6\n", "Nevada 2001 2.4" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi = dfa.set_index('state')" ] }, { "cell_type": "markdown", "id": "593fa040-0718-4af7-8696-679c939e19d1", "metadata": {}, "source": [ "#### Indexing" ] }, { "cell_type": "markdown", "id": "90a5166f-265d-436a-899e-59ae9321761a", "metadata": {}, "source": [ "##### polars" ] }, { "cell_type": "code", "execution_count": 4, "id": "4f2b3ee5-dac9-4a51-9524-d39973ed3b36", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (1, 3)
stateyearpop
stri64f64
"Ohio"20001.5
" ], "text/plain": [ "shape: (1, 3)\n", "┌───────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞═══════╪══════╪═════╡\n", "│ Ohio ┆ 2000 ┆ 1.5 │\n", "└───────┴──────┴─────┘" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[0]" ] }, { "cell_type": "code", "execution_count": 5, "id": "7e14d95a-2e44-4671-9e2a-33552c8a305b", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (1, 3)
stateyearpop
stri64f64
"Ohio"20001.5
" ], "text/plain": [ "shape: (1, 3)\n", "┌───────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞═══════╪══════╪═════╡\n", "│ Ohio ┆ 2000 ┆ 1.5 │\n", "└───────┴──────┴─────┘" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[0:1]" ] }, { "cell_type": "code", "execution_count": 6, "id": "4c71b9cc-09e5-4b9b-8f57-0c2c10632081", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (2, 3)
stateyearpop
stri64f64
"Ohio"20001.5
"Ohio"20011.7
" ], "text/plain": [ "shape: (2, 3)\n", "┌───────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞═══════╪══════╪═════╡\n", "│ Ohio ┆ 2000 ┆ 1.5 │\n", "│ Ohio ┆ 2001 ┆ 1.7 │\n", "└───────┴──────┴─────┘" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[0:2]" ] }, { "cell_type": "markdown", "id": "4d122383-e194-4e9f-a8a6-86b7dd00413a", "metadata": {}, "source": [ "##### pandas" ] }, { "cell_type": "code", "execution_count": 10, "id": "d2ff7e2b-c2cb-45f2-aee7-6bf65a4b5b75", "metadata": {}, "outputs": [ { "ename": "KeyError", "evalue": "0", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mKeyError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexes/base.py:3812\u001b[39m, in \u001b[36mIndex.get_loc\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 3811\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m3812\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_engine\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 3813\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:167\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine.get_loc\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:196\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine.get_loc\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/hashtable_class_helper.pxi:7088\u001b[39m, in \u001b[36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/hashtable_class_helper.pxi:7096\u001b[39m, in \u001b[36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[31mKeyError\u001b[39m: 0", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[31mKeyError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[10]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mdfa\u001b[49m\u001b[43m[\u001b[49m\u001b[32;43m0\u001b[39;49m\u001b[43m]\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/frame.py:4113\u001b[39m, in \u001b[36mDataFrame.__getitem__\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 4111\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m.columns.nlevels > \u001b[32m1\u001b[39m:\n\u001b[32m 4112\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m._getitem_multilevel(key)\n\u001b[32m-> \u001b[39m\u001b[32m4113\u001b[39m indexer = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mcolumns\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 4114\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[32m 4115\u001b[39m indexer = [indexer]\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexes/base.py:3819\u001b[39m, in \u001b[36mIndex.get_loc\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 3814\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[32m 3815\u001b[39m \u001b[38;5;28misinstance\u001b[39m(casted_key, abc.Iterable)\n\u001b[32m 3816\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[32m 3817\u001b[39m ):\n\u001b[32m 3818\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[32m-> \u001b[39m\u001b[32m3819\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01merr\u001b[39;00m\n\u001b[32m 3820\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[32m 3821\u001b[39m \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[32m 3822\u001b[39m \u001b[38;5;66;03m# InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[32m 3823\u001b[39m \u001b[38;5;66;03m# the TypeError.\u001b[39;00m\n\u001b[32m 3824\u001b[39m \u001b[38;5;28mself\u001b[39m._check_indexing_error(key)\n", "\u001b[31mKeyError\u001b[39m: 0" ] } ], "source": [ "dfa[0]" ] }, { "cell_type": "code", "execution_count": 8, "id": "221bd8a2-1705-4549-a9c0-89a8ce2b9aee", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "state Ohio\n", "year 2000\n", "pop 1.5\n", "Name: 0, dtype: object" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.loc[0]" ] }, { "cell_type": "code", "execution_count": 11, "id": "fe2cc9cb-2074-4dc5-96e6-9e3d978c5ef7", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "state Ohio\n", "year 2000\n", "pop 1.5\n", "Name: 0, dtype: object" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.iloc[0]" ] }, { "cell_type": "code", "execution_count": 14, "id": "5d481cbc-c8fb-4059-86fe-c38a844fa420", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pandas.core.series.Series" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(dfa.iloc[0])" ] }, { "cell_type": "code", "execution_count": 12, "id": "3aa3c167-43fa-4aba-82ef-81434bdb7f78", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
0Ohio20001.5
1Ohio20011.7
\n", "
" ], "text/plain": [ " state year pop\n", "0 Ohio 2000 1.5\n", "1 Ohio 2001 1.7" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa[0:2]" ] }, { "cell_type": "code", "execution_count": 13, "id": "31c149e9-4477-42ad-add3-23d5cf06290e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
0Ohio20001.5
1Ohio20011.7
\n", "
" ], "text/plain": [ " state year pop\n", "0 Ohio 2000 1.5\n", "1 Ohio 2001 1.7" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.iloc[0:2]" ] }, { "cell_type": "code", "execution_count": 15, "id": "685d5fae-87ca-4eda-a6ba-100566b50700", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
Ohio20023.6
Nevada20012.4
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6\n", "Nevada 2001 2.4" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi = dfa.set_index('state')" ] }, { "cell_type": "code", "execution_count": 16, "id": "1d8a847b-ff37-45d7-8034-9e883426c331", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
Ohio20023.6
Nevada20012.4
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6\n", "Nevada 2001 2.4" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi" ] }, { "cell_type": "code", "execution_count": 17, "id": "b914e572-a0d0-4953-899e-cad1a8fc49aa", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
Ohio20023.6
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.loc['Ohio']" ] }, { "cell_type": "code", "execution_count": 18, "id": "3b1d9e83-78d9-45be-a455-3599b42769db", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "year 2001.0\n", "pop 2.4\n", "Name: Nevada, dtype: float64" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.loc['Nevada']" ] }, { "cell_type": "code", "execution_count": 19, "id": "92b02bef-e2fc-4dc0-be38-05bc2fa11b28", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.iloc[:2]" ] }, { "cell_type": "code", "execution_count": 20, "id": "9a3d887d-12f7-4dd4-a8c8-26110f7b73fc", "metadata": {}, "outputs": [ { "ename": "KeyError", "evalue": "'Texas'", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mKeyError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexes/base.py:3812\u001b[39m, in \u001b[36mIndex.get_loc\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 3811\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m3812\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_engine\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 3813\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:167\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine.get_loc\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:191\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine.get_loc\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:234\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine._get_loc_duplicates\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:242\u001b[39m, in \u001b[36mpandas._libs.index.IndexEngine._maybe_get_bool_indexer\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32mpandas/_libs/index.pyx:134\u001b[39m, in \u001b[36mpandas._libs.index._unpack_bool_indexer\u001b[39m\u001b[34m()\u001b[39m\n", "\u001b[31mKeyError\u001b[39m: 'Texas'", "\nThe above exception was the direct cause of the following exception:\n", "\u001b[31mKeyError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[20]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mdfi\u001b[49m\u001b[43m.\u001b[49m\u001b[43mloc\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mTexas\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexing.py:1192\u001b[39m, in \u001b[36m_LocationIndexer.__getitem__\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 1190\u001b[39m maybe_callable = com.apply_if_callable(key, \u001b[38;5;28mself\u001b[39m.obj)\n\u001b[32m 1191\u001b[39m maybe_callable = \u001b[38;5;28mself\u001b[39m._check_deprecated_callable_usage(key, maybe_callable)\n\u001b[32m-> \u001b[39m\u001b[32m1192\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_getitem_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmaybe_callable\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[43m=\u001b[49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexing.py:1432\u001b[39m, in \u001b[36m_LocIndexer._getitem_axis\u001b[39m\u001b[34m(self, key, axis)\u001b[39m\n\u001b[32m 1430\u001b[39m \u001b[38;5;66;03m# fall thru to straight lookup\u001b[39;00m\n\u001b[32m 1431\u001b[39m \u001b[38;5;28mself\u001b[39m._validate_key(key, axis)\n\u001b[32m-> \u001b[39m\u001b[32m1432\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_get_label\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[43m=\u001b[49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexing.py:1382\u001b[39m, in \u001b[36m_LocIndexer._get_label\u001b[39m\u001b[34m(self, label, axis)\u001b[39m\n\u001b[32m 1380\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m_get_label\u001b[39m(\u001b[38;5;28mself\u001b[39m, label, axis: AxisInt):\n\u001b[32m 1381\u001b[39m \u001b[38;5;66;03m# GH#5567 this will fail if the label is not present in the axis.\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1382\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43mobj\u001b[49m\u001b[43m.\u001b[49m\u001b[43mxs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlabel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[43m=\u001b[49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/generic.py:4323\u001b[39m, in \u001b[36mNDFrame.xs\u001b[39m\u001b[34m(self, key, axis, level, drop_level)\u001b[39m\n\u001b[32m 4321\u001b[39m new_index = index[loc]\n\u001b[32m 4322\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m-> \u001b[39m\u001b[32m4323\u001b[39m loc = \u001b[43mindex\u001b[49m\u001b[43m.\u001b[49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 4325\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(loc, np.ndarray):\n\u001b[32m 4326\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m loc.dtype == np.bool_:\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/pandas/core/indexes/base.py:3819\u001b[39m, in \u001b[36mIndex.get_loc\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 3814\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[32m 3815\u001b[39m \u001b[38;5;28misinstance\u001b[39m(casted_key, abc.Iterable)\n\u001b[32m 3816\u001b[39m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[32m 3817\u001b[39m ):\n\u001b[32m 3818\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[32m-> \u001b[39m\u001b[32m3819\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34;01merr\u001b[39;00m\n\u001b[32m 3820\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[32m 3821\u001b[39m \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[32m 3822\u001b[39m \u001b[38;5;66;03m# InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[32m 3823\u001b[39m \u001b[38;5;66;03m# the TypeError.\u001b[39;00m\n\u001b[32m 3824\u001b[39m \u001b[38;5;28mself\u001b[39m._check_indexing_error(key)\n", "\u001b[31mKeyError\u001b[39m: 'Texas'" ] } ], "source": [ "dfi.loc['Texas']" ] }, { "cell_type": "code", "execution_count": 21, "id": "d50a695d-4f10-4398-9449-f3ce6a73679a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
Ohio20023.6
Nevada20012.4
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6\n", "Nevada 2001 2.4" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.loc['Ohio':'Nevada'] # inclusive!" ] }, { "cell_type": "code", "execution_count": 22, "id": "a9f277e5-9a47-487f-8eb4-2400819ac200", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Ohio20001.5
Ohio20011.7
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Ohio 2000 1.5\n", "Ohio 2001 1.7" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.iloc[:2] # exclusive" ] }, { "cell_type": "markdown", "id": "c9ae761b-e170-440c-91a6-2e725a152775", "metadata": {}, "source": [ "#### Filtering" ] }, { "cell_type": "code", "execution_count": 23, "id": "0cf67f73-a0f3-4a3f-9240-6274c631b098", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (4,)
pop
bool
false
false
true
true
" ], "text/plain": [ "shape: (4,)\n", "Series: 'pop' [bool]\n", "[\n", "\tfalse\n", "\tfalse\n", "\ttrue\n", "\ttrue\n", "]" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['pop'] > 2" ] }, { "cell_type": "code", "execution_count": 24, "id": "59ef321f-312e-4307-a380-10b41a2f7553", "metadata": {}, "outputs": [ { "ename": "ValueError", "evalue": "expected 3 values when selecting columns by boolean mask, got 4", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mTypeError\u001b[39m Traceback (most recent call last)", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:167\u001b[39m, in \u001b[36mget_df_item_by_key\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 166\u001b[39m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m167\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_select_rows\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m 168\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:319\u001b[39m, in \u001b[36m_select_rows\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 318\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(key, pl.Series):\n\u001b[32m--> \u001b[39m\u001b[32m319\u001b[39m indices = \u001b[43m_convert_series_to_indices\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdf\u001b[49m\u001b[43m.\u001b[49m\u001b[43mheight\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 320\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _select_rows_by_index(df, indices)\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:360\u001b[39m, in \u001b[36m_convert_series_to_indices\u001b[39m\u001b[34m(s, size)\u001b[39m\n\u001b[32m 359\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m s.dtype == Boolean:\n\u001b[32m--> \u001b[39m\u001b[32m360\u001b[39m \u001b[43m_raise_on_boolean_mask\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 361\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:457\u001b[39m, in \u001b[36m_raise_on_boolean_mask\u001b[39m\u001b[34m()\u001b[39m\n\u001b[32m 453\u001b[39m msg = (\n\u001b[32m 454\u001b[39m \u001b[33m\"\u001b[39m\u001b[33mselecting rows by passing a boolean mask to `__getitem__` is not supported\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 455\u001b[39m \u001b[33m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[33mHint: Use the `filter` method instead.\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m 456\u001b[39m )\n\u001b[32m--> \u001b[39m\u001b[32m457\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(msg)\n", "\u001b[31mTypeError\u001b[39m: selecting rows by passing a boolean mask to `__getitem__` is not supported\n\nHint: Use the `filter` method instead.", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[31mValueError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[24]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mpop\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[43m>\u001b[49m\u001b[43m \u001b[49m\u001b[32;43m2\u001b[39;49m\u001b[43m]\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/dataframe/frame.py:1403\u001b[39m, in \u001b[36mDataFrame.__getitem__\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 1266\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m__getitem__\u001b[39m(\n\u001b[32m 1267\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 1268\u001b[39m key: (\n\u001b[32m (...)\u001b[39m\u001b[32m 1277\u001b[39m ),\n\u001b[32m 1278\u001b[39m ) -> DataFrame | Series | Any:\n\u001b[32m 1279\u001b[39m \u001b[38;5;250m \u001b[39m\u001b[33;03m\"\"\"\u001b[39;00m\n\u001b[32m 1280\u001b[39m \u001b[33;03m Get part of the DataFrame as a new DataFrame, Series, or scalar.\u001b[39;00m\n\u001b[32m 1281\u001b[39m \n\u001b[32m (...)\u001b[39m\u001b[32m 1401\u001b[39m \u001b[33;03m └─────┴─────┴─────┘\u001b[39;00m\n\u001b[32m 1402\u001b[39m \u001b[33;03m \"\"\"\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1403\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mget_df_item_by_key\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:169\u001b[39m, in \u001b[36mget_df_item_by_key\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 167\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _select_rows(df, key) \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m 168\u001b[39m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[32m--> \u001b[39m\u001b[32m169\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_select_columns\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:231\u001b[39m, in \u001b[36m_select_columns\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 229\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _select_columns_by_index(df, key)\n\u001b[32m 230\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m dtype == Boolean:\n\u001b[32m--> \u001b[39m\u001b[32m231\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_select_columns_by_mask\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m 232\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 233\u001b[39m msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mcannot select columns using Series of type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdtype\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:277\u001b[39m, in \u001b[36m_select_columns_by_mask\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 275\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(key) != df.width:\n\u001b[32m 276\u001b[39m msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mexpected \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdf.width\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m values when selecting columns by boolean mask, got \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(key)\u001b[38;5;132;01m}\u001b[39;00m\u001b[33m\"\u001b[39m\n\u001b[32m--> \u001b[39m\u001b[32m277\u001b[39m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(msg)\n\u001b[32m 279\u001b[39m indices = (i \u001b[38;5;28;01mfor\u001b[39;00m i, val \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(key) \u001b[38;5;28;01mif\u001b[39;00m val)\n\u001b[32m 280\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _select_columns_by_index(df, indices)\n", "\u001b[31mValueError\u001b[39m: expected 3 values when selecting columns by boolean mask, got 4" ] } ], "source": [ "df[df['pop'] > 2]" ] }, { "cell_type": "code", "execution_count": 25, "id": "cb993d3b-e0b3-4156-97f3-7e31eb3bbe47", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (2, 3)
stateyearpop
stri64f64
"Ohio"20023.6
"Nevada"20012.4
" ], "text/plain": [ "shape: (2, 3)\n", "┌────────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞════════╪══════╪═════╡\n", "│ Ohio ┆ 2002 ┆ 3.6 │\n", "│ Nevada ┆ 2001 ┆ 2.4 │\n", "└────────┴──────┴─────┘" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.filter(pl.col('pop') > 2)" ] }, { "cell_type": "code", "execution_count": 26, "id": "9082b190-8bd1-436c-9fc3-d2f0cbba03d2", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 False\n", "1 False\n", "2 True\n", "3 True\n", "Name: pop, dtype: bool" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa['pop'] > 2" ] }, { "cell_type": "code", "execution_count": 27, "id": "491388c2-75a7-4fb1-be51-69d28eac7cea", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
2Ohio20023.6
3Nevada20012.4
\n", "
" ], "text/plain": [ " state year pop\n", "2 Ohio 2002 3.6\n", "3 Nevada 2001 2.4" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa[dfa['pop'] > 2]" ] }, { "cell_type": "code", "execution_count": 28, "id": "db4bd903-7e9e-4016-9779-cd8a6f5fb44b", "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
2Ohio20023.6
3Nevada20012.4
\n", "
" ], "text/plain": [ " state year pop\n", "2 Ohio 2002 3.6\n", "3 Nevada 2001 2.4" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.query('pop > 2')" ] }, { "cell_type": "markdown", "id": "70d2408d-a125-40db-b8eb-9126abadc699", "metadata": {}, "source": [ "#### Sorting " ] }, { "cell_type": "code", "execution_count": 29, "id": "07c9bbc8-d4fb-4e5d-bbff-b931d3161c64", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (4, 3)
stateyearpop
stri64f64
"Ohio"20001.5
"Ohio"20011.7
"Nevada"20012.4
"Ohio"20023.6
" ], "text/plain": [ "shape: (4, 3)\n", "┌────────┬──────┬─────┐\n", "│ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- │\n", "│ str ┆ i64 ┆ f64 │\n", "╞════════╪══════╪═════╡\n", "│ Ohio ┆ 2000 ┆ 1.5 │\n", "│ Ohio ┆ 2001 ┆ 1.7 │\n", "│ Nevada ┆ 2001 ┆ 2.4 │\n", "│ Ohio ┆ 2002 ┆ 3.6 │\n", "└────────┴──────┴─────┘" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.sort('pop')" ] }, { "cell_type": "code", "execution_count": 30, "id": "cfb89459-16d2-4b1b-8c99-b6e6fc0f66a2", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
0Ohio20001.5
1Ohio20011.7
3Nevada20012.4
2Ohio20023.6
\n", "
" ], "text/plain": [ " state year pop\n", "0 Ohio 2000 1.5\n", "1 Ohio 2001 1.7\n", "3 Nevada 2001 2.4\n", "2 Ohio 2002 3.6" ] }, "execution_count": 30, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.sort_values('pop')" ] }, { "cell_type": "code", "execution_count": 31, "id": "3db0ee27-29e2-4cba-8bb2-5883881bd1ad", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
state
Nevada20012.4
Ohio20001.5
Ohio20011.7
Ohio20023.6
\n", "
" ], "text/plain": [ " year pop\n", "state \n", "Nevada 2001 2.4\n", "Ohio 2000 1.5\n", "Ohio 2001 1.7\n", "Ohio 2002 3.6" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfi.sort_index()" ] }, { "cell_type": "markdown", "id": "2845da74-73ba-4776-965c-a34938662b06", "metadata": {}, "source": [ "#### Describe" ] }, { "cell_type": "code", "execution_count": 32, "id": "6f30c191-3c79-4056-9df0-e6a3b556e16c", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (9, 4)
statisticstateyearpop
strstrf64f64
"count""4"4.04.0
"null_count""0"0.00.0
"mean"null2001.02.3
"std"null0.8164970.948683
"min""Nevada"2000.01.5
"25%"null2001.01.7
"50%"null2001.02.4
"75%"null2001.02.4
"max""Ohio"2002.03.6
" ], "text/plain": [ "shape: (9, 4)\n", "┌────────────┬────────┬──────────┬──────────┐\n", "│ statistic ┆ state ┆ year ┆ pop │\n", "│ --- ┆ --- ┆ --- ┆ --- │\n", "│ str ┆ str ┆ f64 ┆ f64 │\n", "╞════════════╪════════╪══════════╪══════════╡\n", "│ count ┆ 4 ┆ 4.0 ┆ 4.0 │\n", "│ null_count ┆ 0 ┆ 0.0 ┆ 0.0 │\n", "│ mean ┆ null ┆ 2001.0 ┆ 2.3 │\n", "│ std ┆ null ┆ 0.816497 ┆ 0.948683 │\n", "│ min ┆ Nevada ┆ 2000.0 ┆ 1.5 │\n", "│ 25% ┆ null ┆ 2001.0 ┆ 1.7 │\n", "│ 50% ┆ null ┆ 2001.0 ┆ 2.4 │\n", "│ 75% ┆ null ┆ 2001.0 ┆ 2.4 │\n", "│ max ┆ Ohio ┆ 2002.0 ┆ 3.6 │\n", "└────────────┴────────┴──────────┴──────────┘" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.describe()" ] }, { "cell_type": "code", "execution_count": 38, "id": "3c893ffd-da99-4c65-93d5-e1f245e715f6", "metadata": {}, "outputs": [], "source": [ "df.describe()['state'][2]" ] }, { "cell_type": "code", "execution_count": 33, "id": "43d7fe3f-5150-4bcf-acf8-997b9040aba1", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
yearpop
count4.0000004.000000
mean2001.0000002.300000
std0.8164970.948683
min2000.0000001.500000
25%2000.7500001.650000
50%2001.0000002.050000
75%2001.2500002.700000
max2002.0000003.600000
\n", "
" ], "text/plain": [ " year pop\n", "count 4.000000 4.000000\n", "mean 2001.000000 2.300000\n", "std 0.816497 0.948683\n", "min 2000.000000 1.500000\n", "25% 2000.750000 1.650000\n", "50% 2001.000000 2.050000\n", "75% 2001.250000 2.700000\n", "max 2002.000000 3.600000" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.describe()" ] }, { "cell_type": "code", "execution_count": 34, "id": "b8097412-9b62-47a3-a68d-703f745e63bc", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "count 4\n", "unique 2\n", "top Ohio\n", "freq 3\n", "Name: state, dtype: object" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.state.describe()" ] }, { "cell_type": "code", "execution_count": 35, "id": "bef580eb-4d69-4fbd-a320-8efa6a71c429", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
stateyearpop
count44.0000004.000000
unique2NaNNaN
topOhioNaNNaN
freq3NaNNaN
meanNaN2001.0000002.300000
stdNaN0.8164970.948683
minNaN2000.0000001.500000
25%NaN2000.7500001.650000
50%NaN2001.0000002.050000
75%NaN2001.2500002.700000
maxNaN2002.0000003.600000
\n", "
" ], "text/plain": [ " state year pop\n", "count 4 4.000000 4.000000\n", "unique 2 NaN NaN\n", "top Ohio NaN NaN\n", "freq 3 NaN NaN\n", "mean NaN 2001.000000 2.300000\n", "std NaN 0.816497 0.948683\n", "min NaN 2000.000000 1.500000\n", "25% NaN 2000.750000 1.650000\n", "50% NaN 2001.000000 2.050000\n", "75% NaN 2001.250000 2.700000\n", "max NaN 2002.000000 3.600000" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.describe(include='all')" ] }, { "cell_type": "markdown", "id": "0d16a2e1-dfd9-453b-9cbd-f5cfd97d1d72", "metadata": {}, "source": [ "### Penguins Data" ] }, { "cell_type": "code", "execution_count": 40, "id": "31877969-5fee-461b-8e7e-53ad854ed40f", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (344, 17)
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
stri64strstrstrstrstrstrstrf64f64i64i64strf64f64str
"PAL0708"1"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N1A1""Yes""11/11/07"39.118.71813750"MALE"nullnull"Not enough blood for isotopes."
"PAL0708"2"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N1A2""Yes""11/11/07"39.517.41863800"FEMALE"8.94956-24.69454null
"PAL0708"3"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N2A1""Yes""11/16/07"40.318.01953250"FEMALE"8.36821-25.33302null
"PAL0708"4"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N2A2""Yes""11/16/07"nullnullnullnullnullnullnull"Adult not sampled."
"PAL0708"5"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N3A1""Yes""11/16/07"36.719.31933450"FEMALE"8.76651-25.32426null
……………………………………………
"PAL0910"120"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N38A2""No""12/1/09"nullnullnullnullnullnullnullnull
"PAL0910"121"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A1""Yes""11/22/09"46.814.32154850"FEMALE"8.41151-26.13832null
"PAL0910"122"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A2""Yes""11/22/09"50.415.72225750"MALE"8.30166-26.04117null
"PAL0910"123"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A1""Yes""11/22/09"45.214.82125200"FEMALE"8.24246-26.11969null
"PAL0910"124"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A2""Yes""11/22/09"49.916.12135400"MALE"8.3639-26.15531null
" ], "text/plain": [ "shape: (344, 17)\n", "┌───────────┬────────┬─────────────┬────────┬───┬────────┬─────────────┬─────────────┬─────────────┐\n", "│ studyName ┆ Sample ┆ Species ┆ Region ┆ … ┆ Sex ┆ Delta 15 N ┆ Delta 13 C ┆ Comments │\n", "│ --- ┆ Number ┆ --- ┆ --- ┆ ┆ --- ┆ (o/oo) ┆ (o/oo) ┆ --- │\n", "│ str ┆ --- ┆ str ┆ str ┆ ┆ str ┆ --- ┆ --- ┆ str │\n", "│ ┆ i64 ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n", "╞═══════════╪════════╪═════════════╪════════╪═══╪════════╪═════════════╪═════════════╪═════════════╡\n", "│ PAL0708 ┆ 1 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ null ┆ null ┆ Not enough │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ blood for │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ isotopes. │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 2 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.94956 ┆ -24.69454 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 3 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.36821 ┆ -25.33302 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 4 ┆ Adelie ┆ Anvers ┆ … ┆ null ┆ null ┆ null ┆ Adult not │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ sampled. │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 5 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.76651 ┆ -25.32426 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", "│ PAL0910 ┆ 120 ┆ Gentoo ┆ Anvers ┆ … ┆ null ┆ null ┆ null ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 121 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.41151 ┆ -26.13832 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 122 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.30166 ┆ -26.04117 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 123 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.24246 ┆ -26.11969 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 124 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.3639 ┆ -26.15531 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "└───────────┴────────┴─────────────┴────────┴───┴────────┴─────────────┴─────────────┴─────────────┘" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import polars as pl\n", "df = pl.read_csv('penguins_lter.csv')" ] }, { "cell_type": "code", "execution_count": 41, "id": "be31ce9d-2085-48d3-91e7-267fed1c40d2", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (344, 4)
Sample NumberSpeciesRegionIsland
i64strstrstr
1"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen"
2"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen"
3"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen"
4"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen"
5"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen"
…………
120"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe"
121"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe"
122"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe"
123"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe"
124"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe"
" ], "text/plain": [ "shape: (344, 4)\n", "┌───────────────┬─────────────────────────────────┬────────┬───────────┐\n", "│ Sample Number ┆ Species ┆ Region ┆ Island │\n", "│ --- ┆ --- ┆ --- ┆ --- │\n", "│ i64 ┆ str ┆ str ┆ str │\n", "╞═══════════════╪═════════════════════════════════╪════════╪═══════════╡\n", "│ 1 ┆ Adelie Penguin (Pygoscelis ade… ┆ Anvers ┆ Torgersen │\n", "│ 2 ┆ Adelie Penguin (Pygoscelis ade… ┆ Anvers ┆ Torgersen │\n", "│ 3 ┆ Adelie Penguin (Pygoscelis ade… ┆ Anvers ┆ Torgersen │\n", "│ 4 ┆ Adelie Penguin (Pygoscelis ade… ┆ Anvers ┆ Torgersen │\n", "│ 5 ┆ Adelie Penguin (Pygoscelis ade… ┆ Anvers ┆ Torgersen │\n", "│ … ┆ … ┆ … ┆ … │\n", "│ 120 ┆ Gentoo penguin (Pygoscelis pap… ┆ Anvers ┆ Biscoe │\n", "│ 121 ┆ Gentoo penguin (Pygoscelis pap… ┆ Anvers ┆ Biscoe │\n", "│ 122 ┆ Gentoo penguin (Pygoscelis pap… ┆ Anvers ┆ Biscoe │\n", "│ 123 ┆ Gentoo penguin (Pygoscelis pap… ┆ Anvers ┆ Biscoe │\n", "│ 124 ┆ Gentoo penguin (Pygoscelis pap… ┆ Anvers ┆ Biscoe │\n", "└───────────────┴─────────────────────────────────┴────────┴───────────┘" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.select(\n", " 'Sample Number',\n", " 'Species',\n", " 'Region',\n", " 'Island')" ] }, { "cell_type": "code", "execution_count": 42, "id": "471b2827-36cd-4c75-81ae-cc6a803a402c", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Gentoo penguin (Pygoscelis papua)'" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['Species'][341]" ] }, { "cell_type": "code", "execution_count": 43, "id": "c7b9f436-c805-4c89-8b30-30922222d01c", "metadata": {}, "outputs": [ { "ename": "TypeError", "evalue": "argument 'columns': 'int' object cannot be converted to 'PyString'", "output_type": "error", "traceback": [ "\u001b[31m---------------------------------------------------------------------------\u001b[39m", "\u001b[31mTypeError\u001b[39m Traceback (most recent call last)", "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[43]\u001b[39m\u001b[32m, line 1\u001b[39m\n\u001b[32m----> \u001b[39m\u001b[32m1\u001b[39m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mSpecies\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[32;43m341\u001b[39;49m\u001b[43m]\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/dataframe/frame.py:1403\u001b[39m, in \u001b[36mDataFrame.__getitem__\u001b[39m\u001b[34m(self, key)\u001b[39m\n\u001b[32m 1266\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m__getitem__\u001b[39m(\n\u001b[32m 1267\u001b[39m \u001b[38;5;28mself\u001b[39m,\n\u001b[32m 1268\u001b[39m key: (\n\u001b[32m (...)\u001b[39m\u001b[32m 1277\u001b[39m ),\n\u001b[32m 1278\u001b[39m ) -> DataFrame | Series | Any:\n\u001b[32m 1279\u001b[39m \u001b[38;5;250m \u001b[39m\u001b[33;03m\"\"\"\u001b[39;00m\n\u001b[32m 1280\u001b[39m \u001b[33;03m Get part of the DataFrame as a new DataFrame, Series, or scalar.\u001b[39;00m\n\u001b[32m 1281\u001b[39m \n\u001b[32m (...)\u001b[39m\u001b[32m 1401\u001b[39m \u001b[33;03m └─────┴─────┴─────┘\u001b[39;00m\n\u001b[32m 1402\u001b[39m \u001b[33;03m \"\"\"\u001b[39;00m\n\u001b[32m-> \u001b[39m\u001b[32m1403\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mget_df_item_by_key\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:148\u001b[39m, in \u001b[36mget_df_item_by_key\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 146\u001b[39m \u001b[38;5;66;03m# Support df[True, False] and df[\"a\", \"b\"] as these are not ambiguous\u001b[39;00m\n\u001b[32m 147\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(row_key, (\u001b[38;5;28mbool\u001b[39m, \u001b[38;5;28mstr\u001b[39m)):\n\u001b[32m--> \u001b[39m\u001b[32m148\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_select_columns\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m 150\u001b[39m selection = _select_columns(df, col_key)\n\u001b[32m 152\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m selection.is_empty():\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:217\u001b[39m, in \u001b[36m_select_columns\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 215\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m _select_columns_by_index(df, key) \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m 216\u001b[39m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(first, \u001b[38;5;28mstr\u001b[39m):\n\u001b[32m--> \u001b[39m\u001b[32m217\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_select_columns_by_name\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdf\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[32m 218\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[32m 219\u001b[39m msg = \u001b[33mf\u001b[39m\u001b[33m\"\u001b[39m\u001b[33mcannot select columns using Sequence with elements of type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mqualified_type_name(first)\u001b[38;5;132;01m!r}\u001b[39;00m\u001b[33m\"\u001b[39m\n", "\u001b[36mFile \u001b[39m\u001b[32m~/Dropbox/Documents/Teaching/cs503-2026sp/.pixi/envs/default/lib/python3.14/site-packages/polars/_utils/getitem.py:269\u001b[39m, in \u001b[36m_select_columns_by_name\u001b[39m\u001b[34m(df, key)\u001b[39m\n\u001b[32m 268\u001b[39m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[34m_select_columns_by_name\u001b[39m(df: DataFrame, key: Iterable[\u001b[38;5;28mstr\u001b[39m]) -> DataFrame:\n\u001b[32m--> \u001b[39m\u001b[32m269\u001b[39m \u001b[38;5;28;01mreturn\u001b[39;00m df._from_pydf(\u001b[43mdf\u001b[49m\u001b[43m.\u001b[49m\u001b[43m_df\u001b[49m\u001b[43m.\u001b[49m\u001b[43mselect\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m)\n", "\u001b[31mTypeError\u001b[39m: argument 'columns': 'int' object cannot be converted to 'PyString'" ] } ], "source": [ "df['Species',341]" ] }, { "cell_type": "code", "execution_count": 44, "id": "a07475bc-160b-45f1-91ff-26cef2579c19", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Schema([('studyName', String),\n", " ('Sample Number', Int64),\n", " ('Species', String),\n", " ('Region', String),\n", " ('Island', String),\n", " ('Stage', String),\n", " ('Individual ID', String),\n", " ('Clutch Completion', String),\n", " ('Date Egg', String),\n", " ('Culmen Length (mm)', Float64),\n", " ('Culmen Depth (mm)', Float64),\n", " ('Flipper Length (mm)', Int64),\n", " ('Body Mass (g)', Int64),\n", " ('Sex', String),\n", " ('Delta 15 N (o/oo)', Float64),\n", " ('Delta 13 C (o/oo)', Float64),\n", " ('Comments', String)])" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.schema" ] }, { "cell_type": "code", "execution_count": 45, "id": "fff447bb-8541-440c-8d6f-cf20b88d445e", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (168, 17)
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
stri64strstrstrstrstrstrstrf64f64i64i64strf64f64str
"PAL0708"21"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N11A1""Yes""11/12/07"37.818.31743400"FEMALE"8.73762-25.09383null
"PAL0708"22"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N11A2""Yes""11/12/07"37.718.71803600"MALE"8.66271-25.0639null
"PAL0708"23"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N12A1""Yes""11/12/07"35.919.21893800"FEMALE"9.22286-25.03474null
"PAL0708"24"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N12A2""Yes""11/12/07"38.218.11853950"MALE"8.43423-25.22664null
"PAL0708"25"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N13A1""Yes""11/10/07"38.817.21803800"MALE"9.63954-25.29856null
……………………………………………
"PAL0910"120"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N38A2""No""12/1/09"nullnullnullnullnullnullnullnull
"PAL0910"121"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A1""Yes""11/22/09"46.814.32154850"FEMALE"8.41151-26.13832null
"PAL0910"122"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A2""Yes""11/22/09"50.415.72225750"MALE"8.30166-26.04117null
"PAL0910"123"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A1""Yes""11/22/09"45.214.82125200"FEMALE"8.24246-26.11969null
"PAL0910"124"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A2""Yes""11/22/09"49.916.12135400"MALE"8.3639-26.15531null
" ], "text/plain": [ "shape: (168, 17)\n", "┌───────────┬────────┬──────────────┬────────┬───┬────────┬──────────────┬──────────────┬──────────┐\n", "│ studyName ┆ Sample ┆ Species ┆ Region ┆ … ┆ Sex ┆ Delta 15 N ┆ Delta 13 C ┆ Comments │\n", "│ --- ┆ Number ┆ --- ┆ --- ┆ ┆ --- ┆ (o/oo) ┆ (o/oo) ┆ --- │\n", "│ str ┆ --- ┆ str ┆ str ┆ ┆ str ┆ --- ┆ --- ┆ str │\n", "│ ┆ i64 ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n", "╞═══════════╪════════╪══════════════╪════════╪═══╪════════╪══════════════╪══════════════╪══════════╡\n", "│ PAL0708 ┆ 21 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.73762 ┆ -25.09383 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 22 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.66271 ┆ -25.0639 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 23 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 9.22286 ┆ -25.03474 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 24 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.43423 ┆ -25.22664 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 25 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 9.63954 ┆ -25.29856 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", "│ PAL0910 ┆ 120 ┆ Gentoo ┆ Anvers ┆ … ┆ null ┆ null ┆ null ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 121 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.41151 ┆ -26.13832 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 122 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.30166 ┆ -26.04117 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 123 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.24246 ┆ -26.11969 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 124 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.3639 ┆ -26.15531 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "└───────────┴────────┴──────────────┴────────┴───┴────────┴──────────────┴──────────────┴──────────┘" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.filter(pl.col('Island') == \"Biscoe\")" ] }, { "cell_type": "code", "execution_count": 46, "id": "4ec0729b-6500-4681-9776-dd42d577995d", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (242, 17)
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
stri64strstrstrstrstrstrstrf64f64i64i64strf64f64str
"PAL0708"3"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N2A1""Yes""11/16/07"40.318.01953250"FEMALE"8.36821-25.33302null
"PAL0708"10"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N5A2""Yes""11/9/07"42.020.21904250null9.13362-25.09368"No blood sample obtained for s…
"PAL0708"13"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N7A1""Yes""11/15/07"41.117.61823200"FEMALE"nullnull"Not enough blood for isotopes."
"PAL0708"18"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N9A2""Yes""11/12/07"42.520.71974500"MALE"8.67538-25.13993null
"PAL0708"20"Adelie Penguin (Pygoscelis ade…"Anvers""Torgersen""Adult, 1 Egg Stage""N10A2""Yes""11/16/07"46.021.51944200"MALE"9.11616-24.77227null
……………………………………………
"PAL0910"119"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N38A1""No""12/1/09"47.213.72144925"FEMALE"7.99184-26.20538null
"PAL0910"121"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A1""Yes""11/22/09"46.814.32154850"FEMALE"8.41151-26.13832null
"PAL0910"122"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A2""Yes""11/22/09"50.415.72225750"MALE"8.30166-26.04117null
"PAL0910"123"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A1""Yes""11/22/09"45.214.82125200"FEMALE"8.24246-26.11969null
"PAL0910"124"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A2""Yes""11/22/09"49.916.12135400"MALE"8.3639-26.15531null
" ], "text/plain": [ "shape: (242, 17)\n", "┌───────────┬────────┬─────────────┬────────┬───┬────────┬─────────────┬─────────────┬─────────────┐\n", "│ studyName ┆ Sample ┆ Species ┆ Region ┆ … ┆ Sex ┆ Delta 15 N ┆ Delta 13 C ┆ Comments │\n", "│ --- ┆ Number ┆ --- ┆ --- ┆ ┆ --- ┆ (o/oo) ┆ (o/oo) ┆ --- │\n", "│ str ┆ --- ┆ str ┆ str ┆ ┆ str ┆ --- ┆ --- ┆ str │\n", "│ ┆ i64 ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n", "╞═══════════╪════════╪═════════════╪════════╪═══╪════════╪═════════════╪═════════════╪═════════════╡\n", "│ PAL0708 ┆ 3 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.36821 ┆ -25.33302 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 10 ┆ Adelie ┆ Anvers ┆ … ┆ null ┆ 9.13362 ┆ -25.09368 ┆ No blood │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ sample │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ obtained │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ for s… │\n", "│ PAL0708 ┆ 13 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ null ┆ null ┆ Not enough │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ blood for │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ isotopes. │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 18 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.67538 ┆ -25.13993 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 20 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 9.11616 ┆ -24.77227 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", "│ PAL0910 ┆ 119 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 7.99184 ┆ -26.20538 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 121 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.41151 ┆ -26.13832 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 122 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.30166 ┆ -26.04117 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 123 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.24246 ┆ -26.11969 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 124 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.3639 ┆ -26.15531 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "└───────────┴────────┴─────────────┴────────┴───┴────────┴─────────────┴─────────────┴─────────────┘" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.filter(pl.col(\"Culmen Length (mm)\") > 40)" ] }, { "cell_type": "code", "execution_count": 47, "id": "967ef673-7bfc-4fb2-b376-67fe2fbef3da", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (139, 17)
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
stri64strstrstrstrstrstrstrf64f64i64i64strf64f64str
"PAL0708"27"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N17A1""Yes""11/12/07"40.618.61833550"MALE"8.93997-25.36288null
"PAL0708"28"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N17A2""Yes""11/12/07"40.517.91873200"FEMALE"8.08138-25.49448null
"PAL0708"30"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N18A2""No""11/10/07"40.518.91803950"MALE"8.90027-25.11609"Nest never observed with full …
"PAL0809"52"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N21A2""Yes""11/6/08"40.118.91884300"MALE"8.51362-26.55602null
"PAL0809"54"Adelie Penguin (Pygoscelis ade…"Anvers""Biscoe""Adult, 1 Egg Stage""N22A2""Yes""11/9/08"42.019.52004050"MALE"8.48095-26.3146null
……………………………………………
"PAL0910"119"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N38A1""No""12/1/09"47.213.72144925"FEMALE"7.99184-26.20538null
"PAL0910"121"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A1""Yes""11/22/09"46.814.32154850"FEMALE"8.41151-26.13832null
"PAL0910"122"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N39A2""Yes""11/22/09"50.415.72225750"MALE"8.30166-26.04117null
"PAL0910"123"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A1""Yes""11/22/09"45.214.82125200"FEMALE"8.24246-26.11969null
"PAL0910"124"Gentoo penguin (Pygoscelis pap…"Anvers""Biscoe""Adult, 1 Egg Stage""N43A2""Yes""11/22/09"49.916.12135400"MALE"8.3639-26.15531null
" ], "text/plain": [ "shape: (139, 17)\n", "┌───────────┬────────┬─────────────┬────────┬───┬────────┬─────────────┬─────────────┬─────────────┐\n", "│ studyName ┆ Sample ┆ Species ┆ Region ┆ … ┆ Sex ┆ Delta 15 N ┆ Delta 13 C ┆ Comments │\n", "│ --- ┆ Number ┆ --- ┆ --- ┆ ┆ --- ┆ (o/oo) ┆ (o/oo) ┆ --- │\n", "│ str ┆ --- ┆ str ┆ str ┆ ┆ str ┆ --- ┆ --- ┆ str │\n", "│ ┆ i64 ┆ ┆ ┆ ┆ ┆ f64 ┆ f64 ┆ │\n", "╞═══════════╪════════╪═════════════╪════════╪═══╪════════╪═════════════╪═════════════╪═════════════╡\n", "│ PAL0708 ┆ 27 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.93997 ┆ -25.36288 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 28 ┆ Adelie ┆ Anvers ┆ … ┆ FEMALE ┆ 8.08138 ┆ -25.49448 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0708 ┆ 30 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.90027 ┆ -25.11609 ┆ Nest never │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ observed │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ with full … │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0809 ┆ 52 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.51362 ┆ -26.55602 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0809 ┆ 54 ┆ Adelie ┆ Anvers ┆ … ┆ MALE ┆ 8.48095 ┆ -26.3146 ┆ null │\n", "│ ┆ ┆ Penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ ade… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … ┆ … │\n", "│ PAL0910 ┆ 119 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 7.99184 ┆ -26.20538 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 121 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.41151 ┆ -26.13832 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 122 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.30166 ┆ -26.04117 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 123 ┆ Gentoo ┆ Anvers ┆ … ┆ FEMALE ┆ 8.24246 ┆ -26.11969 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ PAL0910 ┆ 124 ┆ Gentoo ┆ Anvers ┆ … ┆ MALE ┆ 8.3639 ┆ -26.15531 ┆ null │\n", "│ ┆ ┆ penguin ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ (Pygoscelis ┆ ┆ ┆ ┆ ┆ ┆ │\n", "│ ┆ ┆ pap… ┆ ┆ ┆ ┆ ┆ ┆ │\n", "└───────────┴────────┴─────────────┴────────┴───┴────────┴─────────────┴─────────────┴─────────────┘" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.filter((pl.col(\"Culmen Length (mm)\") > 40) & (pl.col(\"Island\") == \"Biscoe\"))" ] }, { "cell_type": "code", "execution_count": 48, "id": "3811ae71-fa9c-43cf-a801-e1fb92af24c2", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (3,)
Island
str
"Torgersen"
"Dream"
"Biscoe"
" ], "text/plain": [ "shape: (3,)\n", "Series: 'Island' [str]\n", "[\n", "\t\"Torgersen\"\n", "\t\"Dream\"\n", "\t\"Biscoe\"\n", "]" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['Island'].unique()" ] }, { "cell_type": "code", "execution_count": 49, "id": "2cf86b0d-c256-4436-b990-27e7db80ed73", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (3, 2)
Islandcount
stru32
"Dream"124
"Biscoe"168
"Torgersen"52
" ], "text/plain": [ "shape: (3, 2)\n", "┌───────────┬───────┐\n", "│ Island ┆ count │\n", "│ --- ┆ --- │\n", "│ str ┆ u32 │\n", "╞═══════════╪═══════╡\n", "│ Dream ┆ 124 │\n", "│ Biscoe ┆ 168 │\n", "│ Torgersen ┆ 52 │\n", "└───────────┴───────┘" ] }, "execution_count": 49, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df['Island'].value_counts()" ] }, { "cell_type": "code", "execution_count": 50, "id": "6cda93e4-aab8-4677-a097-8b7e199f00af", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "shape: (3, 2)
IslandCulmen Length (mm)
strf64
"Torgersen"38.95098
"Biscoe"45.257485
"Dream"44.167742
" ], "text/plain": [ "shape: (3, 2)\n", "┌───────────┬────────────────────┐\n", "│ Island ┆ Culmen Length (mm) │\n", "│ --- ┆ --- │\n", "│ str ┆ f64 │\n", "╞═══════════╪════════════════════╡\n", "│ Torgersen ┆ 38.95098 │\n", "│ Biscoe ┆ 45.257485 │\n", "│ Dream ┆ 44.167742 │\n", "└───────────┴────────────────────┘" ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.group_by('Island').agg(pl.col('Culmen Length (mm)').mean())" ] }, { "cell_type": "markdown", "id": "9b1ce18d-3611-4408-a486-b59ab23d2694", "metadata": {}, "source": [ "##### pandas" ] }, { "cell_type": "code", "execution_count": 51, "id": "66506c78-eb24-4938-95e9-5a0c71a96944", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
0PAL07081Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN1A1Yes11/11/0739.118.7181.03750.0MALENaNNaNNot enough blood for isotopes.
1PAL07082Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN1A2Yes11/11/0739.517.4186.03800.0FEMALE8.94956-24.69454NaN
2PAL07083Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN2A1Yes11/16/0740.318.0195.03250.0FEMALE8.36821-25.33302NaN
3PAL07084Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN2A2Yes11/16/07NaNNaNNaNNaNNaNNaNNaNAdult not sampled.
4PAL07085Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN3A1Yes11/16/0736.719.3193.03450.0FEMALE8.76651-25.32426NaN
......................................................
339PAL0910120Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN38A2No12/1/09NaNNaNNaNNaNNaNNaNNaNNaN
340PAL0910121Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A1Yes11/22/0946.814.3215.04850.0FEMALE8.41151-26.13832NaN
341PAL0910122Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A2Yes11/22/0950.415.7222.05750.0MALE8.30166-26.04117NaN
342PAL0910123Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A1Yes11/22/0945.214.8212.05200.0FEMALE8.24246-26.11969NaN
343PAL0910124Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A2Yes11/22/0949.916.1213.05400.0MALE8.36390-26.15531NaN
\n", "

344 rows × 17 columns

\n", "
" ], "text/plain": [ " studyName Sample Number Species Region \\\n", "0 PAL0708 1 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "1 PAL0708 2 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "2 PAL0708 3 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "3 PAL0708 4 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "4 PAL0708 5 Adelie Penguin (Pygoscelis adeliae) Anvers \n", ".. ... ... ... ... \n", "339 PAL0910 120 Gentoo penguin (Pygoscelis papua) Anvers \n", "340 PAL0910 121 Gentoo penguin (Pygoscelis papua) Anvers \n", "341 PAL0910 122 Gentoo penguin (Pygoscelis papua) Anvers \n", "342 PAL0910 123 Gentoo penguin (Pygoscelis papua) Anvers \n", "343 PAL0910 124 Gentoo penguin (Pygoscelis papua) Anvers \n", "\n", " Island Stage Individual ID Clutch Completion Date Egg \\\n", "0 Torgersen Adult, 1 Egg Stage N1A1 Yes 11/11/07 \n", "1 Torgersen Adult, 1 Egg Stage N1A2 Yes 11/11/07 \n", "2 Torgersen Adult, 1 Egg Stage N2A1 Yes 11/16/07 \n", "3 Torgersen Adult, 1 Egg Stage N2A2 Yes 11/16/07 \n", "4 Torgersen Adult, 1 Egg Stage N3A1 Yes 11/16/07 \n", ".. ... ... ... ... ... \n", "339 Biscoe Adult, 1 Egg Stage N38A2 No 12/1/09 \n", "340 Biscoe Adult, 1 Egg Stage N39A1 Yes 11/22/09 \n", "341 Biscoe Adult, 1 Egg Stage N39A2 Yes 11/22/09 \n", "342 Biscoe Adult, 1 Egg Stage N43A1 Yes 11/22/09 \n", "343 Biscoe Adult, 1 Egg Stage N43A2 Yes 11/22/09 \n", "\n", " Culmen Length (mm) Culmen Depth (mm) Flipper Length (mm) \\\n", "0 39.1 18.7 181.0 \n", "1 39.5 17.4 186.0 \n", "2 40.3 18.0 195.0 \n", "3 NaN NaN NaN \n", "4 36.7 19.3 193.0 \n", ".. ... ... ... \n", "339 NaN NaN NaN \n", "340 46.8 14.3 215.0 \n", "341 50.4 15.7 222.0 \n", "342 45.2 14.8 212.0 \n", "343 49.9 16.1 213.0 \n", "\n", " Body Mass (g) Sex Delta 15 N (o/oo) Delta 13 C (o/oo) \\\n", "0 3750.0 MALE NaN NaN \n", "1 3800.0 FEMALE 8.94956 -24.69454 \n", "2 3250.0 FEMALE 8.36821 -25.33302 \n", "3 NaN NaN NaN NaN \n", "4 3450.0 FEMALE 8.76651 -25.32426 \n", ".. ... ... ... ... \n", "339 NaN NaN NaN NaN \n", "340 4850.0 FEMALE 8.41151 -26.13832 \n", "341 5750.0 MALE 8.30166 -26.04117 \n", "342 5200.0 FEMALE 8.24246 -26.11969 \n", "343 5400.0 MALE 8.36390 -26.15531 \n", "\n", " Comments \n", "0 Not enough blood for isotopes. \n", "1 NaN \n", "2 NaN \n", "3 Adult not sampled. \n", "4 NaN \n", ".. ... \n", "339 NaN \n", "340 NaN \n", "341 NaN \n", "342 NaN \n", "343 NaN \n", "\n", "[344 rows x 17 columns]" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "dfa = pd.read_csv('penguins_lter.csv')" ] }, { "cell_type": "code", "execution_count": 52, "id": "bab9e298-c59b-4533-b429-b826e49bc4a5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 344 entries, 0 to 343\n", "Data columns (total 17 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 studyName 344 non-null object \n", " 1 Sample Number 344 non-null int64 \n", " 2 Species 344 non-null object \n", " 3 Region 344 non-null object \n", " 4 Island 344 non-null object \n", " 5 Stage 344 non-null object \n", " 6 Individual ID 344 non-null object \n", " 7 Clutch Completion 344 non-null object \n", " 8 Date Egg 344 non-null object \n", " 9 Culmen Length (mm) 342 non-null float64\n", " 10 Culmen Depth (mm) 342 non-null float64\n", " 11 Flipper Length (mm) 342 non-null float64\n", " 12 Body Mass (g) 342 non-null float64\n", " 13 Sex 334 non-null object \n", " 14 Delta 15 N (o/oo) 330 non-null float64\n", " 15 Delta 13 C (o/oo) 331 non-null float64\n", " 16 Comments 26 non-null object \n", "dtypes: float64(6), int64(1), object(10)\n", "memory usage: 45.8+ KB\n" ] } ], "source": [ "dfa.info()" ] }, { "cell_type": "code", "execution_count": 53, "id": "d4477d3a-321e-4f71-a236-cbdc6283b129", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
20PAL070821Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN11A1Yes11/12/0737.818.3174.03400.0FEMALE8.73762-25.09383NaN
21PAL070822Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN11A2Yes11/12/0737.718.7180.03600.0MALE8.66271-25.06390NaN
22PAL070823Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN12A1Yes11/12/0735.919.2189.03800.0FEMALE9.22286-25.03474NaN
23PAL070824Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN12A2Yes11/12/0738.218.1185.03950.0MALE8.43423-25.22664NaN
24PAL070825Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN13A1Yes11/10/0738.817.2180.03800.0MALE9.63954-25.29856NaN
......................................................
339PAL0910120Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN38A2No12/1/09NaNNaNNaNNaNNaNNaNNaNNaN
340PAL0910121Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A1Yes11/22/0946.814.3215.04850.0FEMALE8.41151-26.13832NaN
341PAL0910122Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A2Yes11/22/0950.415.7222.05750.0MALE8.30166-26.04117NaN
342PAL0910123Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A1Yes11/22/0945.214.8212.05200.0FEMALE8.24246-26.11969NaN
343PAL0910124Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A2Yes11/22/0949.916.1213.05400.0MALE8.36390-26.15531NaN
\n", "

168 rows × 17 columns

\n", "
" ], "text/plain": [ " studyName Sample Number Species Region \\\n", "20 PAL0708 21 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "21 PAL0708 22 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "22 PAL0708 23 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "23 PAL0708 24 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "24 PAL0708 25 Adelie Penguin (Pygoscelis adeliae) Anvers \n", ".. ... ... ... ... \n", "339 PAL0910 120 Gentoo penguin (Pygoscelis papua) Anvers \n", "340 PAL0910 121 Gentoo penguin (Pygoscelis papua) Anvers \n", "341 PAL0910 122 Gentoo penguin (Pygoscelis papua) Anvers \n", "342 PAL0910 123 Gentoo penguin (Pygoscelis papua) Anvers \n", "343 PAL0910 124 Gentoo penguin (Pygoscelis papua) Anvers \n", "\n", " Island Stage Individual ID Clutch Completion Date Egg \\\n", "20 Biscoe Adult, 1 Egg Stage N11A1 Yes 11/12/07 \n", "21 Biscoe Adult, 1 Egg Stage N11A2 Yes 11/12/07 \n", "22 Biscoe Adult, 1 Egg Stage N12A1 Yes 11/12/07 \n", "23 Biscoe Adult, 1 Egg Stage N12A2 Yes 11/12/07 \n", "24 Biscoe Adult, 1 Egg Stage N13A1 Yes 11/10/07 \n", ".. ... ... ... ... ... \n", "339 Biscoe Adult, 1 Egg Stage N38A2 No 12/1/09 \n", "340 Biscoe Adult, 1 Egg Stage N39A1 Yes 11/22/09 \n", "341 Biscoe Adult, 1 Egg Stage N39A2 Yes 11/22/09 \n", "342 Biscoe Adult, 1 Egg Stage N43A1 Yes 11/22/09 \n", "343 Biscoe Adult, 1 Egg Stage N43A2 Yes 11/22/09 \n", "\n", " Culmen Length (mm) Culmen Depth (mm) Flipper Length (mm) \\\n", "20 37.8 18.3 174.0 \n", "21 37.7 18.7 180.0 \n", "22 35.9 19.2 189.0 \n", "23 38.2 18.1 185.0 \n", "24 38.8 17.2 180.0 \n", ".. ... ... ... \n", "339 NaN NaN NaN \n", "340 46.8 14.3 215.0 \n", "341 50.4 15.7 222.0 \n", "342 45.2 14.8 212.0 \n", "343 49.9 16.1 213.0 \n", "\n", " Body Mass (g) Sex Delta 15 N (o/oo) Delta 13 C (o/oo) Comments \n", "20 3400.0 FEMALE 8.73762 -25.09383 NaN \n", "21 3600.0 MALE 8.66271 -25.06390 NaN \n", "22 3800.0 FEMALE 9.22286 -25.03474 NaN \n", "23 3950.0 MALE 8.43423 -25.22664 NaN \n", "24 3800.0 MALE 9.63954 -25.29856 NaN \n", ".. ... ... ... ... ... \n", "339 NaN NaN NaN NaN NaN \n", "340 4850.0 FEMALE 8.41151 -26.13832 NaN \n", "341 5750.0 MALE 8.30166 -26.04117 NaN \n", "342 5200.0 FEMALE 8.24246 -26.11969 NaN \n", "343 5400.0 MALE 8.36390 -26.15531 NaN \n", "\n", "[168 rows x 17 columns]" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa[dfa.Island == 'Biscoe']" ] }, { "cell_type": "code", "execution_count": 54, "id": "f75838ec-e7ae-4dcb-aab9-2427f1cdde40", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
2PAL07083Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN2A1Yes11/16/0740.318.0195.03250.0FEMALE8.36821-25.33302NaN
9PAL070810Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN5A2Yes11/9/0742.020.2190.04250.0NaN9.13362-25.09368No blood sample obtained for sexing.
12PAL070813Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN7A1Yes11/15/0741.117.6182.03200.0FEMALENaNNaNNot enough blood for isotopes.
17PAL070818Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN9A2Yes11/12/0742.520.7197.04500.0MALE8.67538-25.13993NaN
19PAL070820Adelie Penguin (Pygoscelis adeliae)AnversTorgersenAdult, 1 Egg StageN10A2Yes11/16/0746.021.5194.04200.0MALE9.11616-24.77227NaN
......................................................
338PAL0910119Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN38A1No12/1/0947.213.7214.04925.0FEMALE7.99184-26.20538NaN
340PAL0910121Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A1Yes11/22/0946.814.3215.04850.0FEMALE8.41151-26.13832NaN
341PAL0910122Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A2Yes11/22/0950.415.7222.05750.0MALE8.30166-26.04117NaN
342PAL0910123Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A1Yes11/22/0945.214.8212.05200.0FEMALE8.24246-26.11969NaN
343PAL0910124Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A2Yes11/22/0949.916.1213.05400.0MALE8.36390-26.15531NaN
\n", "

242 rows × 17 columns

\n", "
" ], "text/plain": [ " studyName Sample Number Species Region \\\n", "2 PAL0708 3 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "9 PAL0708 10 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "12 PAL0708 13 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "17 PAL0708 18 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "19 PAL0708 20 Adelie Penguin (Pygoscelis adeliae) Anvers \n", ".. ... ... ... ... \n", "338 PAL0910 119 Gentoo penguin (Pygoscelis papua) Anvers \n", "340 PAL0910 121 Gentoo penguin (Pygoscelis papua) Anvers \n", "341 PAL0910 122 Gentoo penguin (Pygoscelis papua) Anvers \n", "342 PAL0910 123 Gentoo penguin (Pygoscelis papua) Anvers \n", "343 PAL0910 124 Gentoo penguin (Pygoscelis papua) Anvers \n", "\n", " Island Stage Individual ID Clutch Completion Date Egg \\\n", "2 Torgersen Adult, 1 Egg Stage N2A1 Yes 11/16/07 \n", "9 Torgersen Adult, 1 Egg Stage N5A2 Yes 11/9/07 \n", "12 Torgersen Adult, 1 Egg Stage N7A1 Yes 11/15/07 \n", "17 Torgersen Adult, 1 Egg Stage N9A2 Yes 11/12/07 \n", "19 Torgersen Adult, 1 Egg Stage N10A2 Yes 11/16/07 \n", ".. ... ... ... ... ... \n", "338 Biscoe Adult, 1 Egg Stage N38A1 No 12/1/09 \n", "340 Biscoe Adult, 1 Egg Stage N39A1 Yes 11/22/09 \n", "341 Biscoe Adult, 1 Egg Stage N39A2 Yes 11/22/09 \n", "342 Biscoe Adult, 1 Egg Stage N43A1 Yes 11/22/09 \n", "343 Biscoe Adult, 1 Egg Stage N43A2 Yes 11/22/09 \n", "\n", " Culmen Length (mm) Culmen Depth (mm) Flipper Length (mm) \\\n", "2 40.3 18.0 195.0 \n", "9 42.0 20.2 190.0 \n", "12 41.1 17.6 182.0 \n", "17 42.5 20.7 197.0 \n", "19 46.0 21.5 194.0 \n", ".. ... ... ... \n", "338 47.2 13.7 214.0 \n", "340 46.8 14.3 215.0 \n", "341 50.4 15.7 222.0 \n", "342 45.2 14.8 212.0 \n", "343 49.9 16.1 213.0 \n", "\n", " Body Mass (g) Sex Delta 15 N (o/oo) Delta 13 C (o/oo) \\\n", "2 3250.0 FEMALE 8.36821 -25.33302 \n", "9 4250.0 NaN 9.13362 -25.09368 \n", "12 3200.0 FEMALE NaN NaN \n", "17 4500.0 MALE 8.67538 -25.13993 \n", "19 4200.0 MALE 9.11616 -24.77227 \n", ".. ... ... ... ... \n", "338 4925.0 FEMALE 7.99184 -26.20538 \n", "340 4850.0 FEMALE 8.41151 -26.13832 \n", "341 5750.0 MALE 8.30166 -26.04117 \n", "342 5200.0 FEMALE 8.24246 -26.11969 \n", "343 5400.0 MALE 8.36390 -26.15531 \n", "\n", " Comments \n", "2 NaN \n", "9 No blood sample obtained for sexing. \n", "12 Not enough blood for isotopes. \n", "17 NaN \n", "19 NaN \n", ".. ... \n", "338 NaN \n", "340 NaN \n", "341 NaN \n", "342 NaN \n", "343 NaN \n", "\n", "[242 rows x 17 columns]" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.query('`Culmen Length (mm)` > 40')" ] }, { "cell_type": "code", "execution_count": 55, "id": "38c69c9d-3025-4e1e-9f10-e954f4ab0b36", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
26PAL070827Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN17A1Yes11/12/0740.618.6183.03550.0MALE8.93997-25.36288NaN
27PAL070828Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN17A2Yes11/12/0740.517.9187.03200.0FEMALE8.08138-25.49448NaN
29PAL070830Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN18A2No11/10/0740.518.9180.03950.0MALE8.90027-25.11609Nest never observed with full clutch.
51PAL080952Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN21A2Yes11/6/0840.118.9188.04300.0MALE8.51362-26.55602NaN
53PAL080954Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN22A2Yes11/9/0842.019.5200.04050.0MALE8.48095-26.31460NaN
......................................................
338PAL0910119Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN38A1No12/1/0947.213.7214.04925.0FEMALE7.99184-26.20538NaN
340PAL0910121Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A1Yes11/22/0946.814.3215.04850.0FEMALE8.41151-26.13832NaN
341PAL0910122Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A2Yes11/22/0950.415.7222.05750.0MALE8.30166-26.04117NaN
342PAL0910123Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A1Yes11/22/0945.214.8212.05200.0FEMALE8.24246-26.11969NaN
343PAL0910124Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A2Yes11/22/0949.916.1213.05400.0MALE8.36390-26.15531NaN
\n", "

139 rows × 17 columns

\n", "
" ], "text/plain": [ " studyName Sample Number Species Region \\\n", "26 PAL0708 27 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "27 PAL0708 28 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "29 PAL0708 30 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "51 PAL0809 52 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "53 PAL0809 54 Adelie Penguin (Pygoscelis adeliae) Anvers \n", ".. ... ... ... ... \n", "338 PAL0910 119 Gentoo penguin (Pygoscelis papua) Anvers \n", "340 PAL0910 121 Gentoo penguin (Pygoscelis papua) Anvers \n", "341 PAL0910 122 Gentoo penguin (Pygoscelis papua) Anvers \n", "342 PAL0910 123 Gentoo penguin (Pygoscelis papua) Anvers \n", "343 PAL0910 124 Gentoo penguin (Pygoscelis papua) Anvers \n", "\n", " Island Stage Individual ID Clutch Completion Date Egg \\\n", "26 Biscoe Adult, 1 Egg Stage N17A1 Yes 11/12/07 \n", "27 Biscoe Adult, 1 Egg Stage N17A2 Yes 11/12/07 \n", "29 Biscoe Adult, 1 Egg Stage N18A2 No 11/10/07 \n", "51 Biscoe Adult, 1 Egg Stage N21A2 Yes 11/6/08 \n", "53 Biscoe Adult, 1 Egg Stage N22A2 Yes 11/9/08 \n", ".. ... ... ... ... ... \n", "338 Biscoe Adult, 1 Egg Stage N38A1 No 12/1/09 \n", "340 Biscoe Adult, 1 Egg Stage N39A1 Yes 11/22/09 \n", "341 Biscoe Adult, 1 Egg Stage N39A2 Yes 11/22/09 \n", "342 Biscoe Adult, 1 Egg Stage N43A1 Yes 11/22/09 \n", "343 Biscoe Adult, 1 Egg Stage N43A2 Yes 11/22/09 \n", "\n", " Culmen Length (mm) Culmen Depth (mm) Flipper Length (mm) \\\n", "26 40.6 18.6 183.0 \n", "27 40.5 17.9 187.0 \n", "29 40.5 18.9 180.0 \n", "51 40.1 18.9 188.0 \n", "53 42.0 19.5 200.0 \n", ".. ... ... ... \n", "338 47.2 13.7 214.0 \n", "340 46.8 14.3 215.0 \n", "341 50.4 15.7 222.0 \n", "342 45.2 14.8 212.0 \n", "343 49.9 16.1 213.0 \n", "\n", " Body Mass (g) Sex Delta 15 N (o/oo) Delta 13 C (o/oo) \\\n", "26 3550.0 MALE 8.93997 -25.36288 \n", "27 3200.0 FEMALE 8.08138 -25.49448 \n", "29 3950.0 MALE 8.90027 -25.11609 \n", "51 4300.0 MALE 8.51362 -26.55602 \n", "53 4050.0 MALE 8.48095 -26.31460 \n", ".. ... ... ... ... \n", "338 4925.0 FEMALE 7.99184 -26.20538 \n", "340 4850.0 FEMALE 8.41151 -26.13832 \n", "341 5750.0 MALE 8.30166 -26.04117 \n", "342 5200.0 FEMALE 8.24246 -26.11969 \n", "343 5400.0 MALE 8.36390 -26.15531 \n", "\n", " Comments \n", "26 NaN \n", "27 NaN \n", "29 Nest never observed with full clutch. \n", "51 NaN \n", "53 NaN \n", ".. ... \n", "338 NaN \n", "340 NaN \n", "341 NaN \n", "342 NaN \n", "343 NaN \n", "\n", "[139 rows x 17 columns]" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa[(dfa.Island == \"Biscoe\") & (dfa['Culmen Length (mm)'] > 40)]" ] }, { "cell_type": "code", "execution_count": 56, "id": "afaeafbb-b336-4cc0-8bc5-7e10dc92fdf4", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
studyNameSample NumberSpeciesRegionIslandStageIndividual IDClutch CompletionDate EggCulmen Length (mm)Culmen Depth (mm)Flipper Length (mm)Body Mass (g)SexDelta 15 N (o/oo)Delta 13 C (o/oo)Comments
26PAL070827Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN17A1Yes11/12/0740.618.6183.03550.0MALE8.93997-25.36288NaN
27PAL070828Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN17A2Yes11/12/0740.517.9187.03200.0FEMALE8.08138-25.49448NaN
29PAL070830Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN18A2No11/10/0740.518.9180.03950.0MALE8.90027-25.11609Nest never observed with full clutch.
51PAL080952Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN21A2Yes11/6/0840.118.9188.04300.0MALE8.51362-26.55602NaN
53PAL080954Adelie Penguin (Pygoscelis adeliae)AnversBiscoeAdult, 1 Egg StageN22A2Yes11/9/0842.019.5200.04050.0MALE8.48095-26.31460NaN
......................................................
338PAL0910119Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN38A1No12/1/0947.213.7214.04925.0FEMALE7.99184-26.20538NaN
340PAL0910121Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A1Yes11/22/0946.814.3215.04850.0FEMALE8.41151-26.13832NaN
341PAL0910122Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN39A2Yes11/22/0950.415.7222.05750.0MALE8.30166-26.04117NaN
342PAL0910123Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A1Yes11/22/0945.214.8212.05200.0FEMALE8.24246-26.11969NaN
343PAL0910124Gentoo penguin (Pygoscelis papua)AnversBiscoeAdult, 1 Egg StageN43A2Yes11/22/0949.916.1213.05400.0MALE8.36390-26.15531NaN
\n", "

139 rows × 17 columns

\n", "
" ], "text/plain": [ " studyName Sample Number Species Region \\\n", "26 PAL0708 27 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "27 PAL0708 28 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "29 PAL0708 30 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "51 PAL0809 52 Adelie Penguin (Pygoscelis adeliae) Anvers \n", "53 PAL0809 54 Adelie Penguin (Pygoscelis adeliae) Anvers \n", ".. ... ... ... ... \n", "338 PAL0910 119 Gentoo penguin (Pygoscelis papua) Anvers \n", "340 PAL0910 121 Gentoo penguin (Pygoscelis papua) Anvers \n", "341 PAL0910 122 Gentoo penguin (Pygoscelis papua) Anvers \n", "342 PAL0910 123 Gentoo penguin (Pygoscelis papua) Anvers \n", "343 PAL0910 124 Gentoo penguin (Pygoscelis papua) Anvers \n", "\n", " Island Stage Individual ID Clutch Completion Date Egg \\\n", "26 Biscoe Adult, 1 Egg Stage N17A1 Yes 11/12/07 \n", "27 Biscoe Adult, 1 Egg Stage N17A2 Yes 11/12/07 \n", "29 Biscoe Adult, 1 Egg Stage N18A2 No 11/10/07 \n", "51 Biscoe Adult, 1 Egg Stage N21A2 Yes 11/6/08 \n", "53 Biscoe Adult, 1 Egg Stage N22A2 Yes 11/9/08 \n", ".. ... ... ... ... ... \n", "338 Biscoe Adult, 1 Egg Stage N38A1 No 12/1/09 \n", "340 Biscoe Adult, 1 Egg Stage N39A1 Yes 11/22/09 \n", "341 Biscoe Adult, 1 Egg Stage N39A2 Yes 11/22/09 \n", "342 Biscoe Adult, 1 Egg Stage N43A1 Yes 11/22/09 \n", "343 Biscoe Adult, 1 Egg Stage N43A2 Yes 11/22/09 \n", "\n", " Culmen Length (mm) Culmen Depth (mm) Flipper Length (mm) \\\n", "26 40.6 18.6 183.0 \n", "27 40.5 17.9 187.0 \n", "29 40.5 18.9 180.0 \n", "51 40.1 18.9 188.0 \n", "53 42.0 19.5 200.0 \n", ".. ... ... ... \n", "338 47.2 13.7 214.0 \n", "340 46.8 14.3 215.0 \n", "341 50.4 15.7 222.0 \n", "342 45.2 14.8 212.0 \n", "343 49.9 16.1 213.0 \n", "\n", " Body Mass (g) Sex Delta 15 N (o/oo) Delta 13 C (o/oo) \\\n", "26 3550.0 MALE 8.93997 -25.36288 \n", "27 3200.0 FEMALE 8.08138 -25.49448 \n", "29 3950.0 MALE 8.90027 -25.11609 \n", "51 4300.0 MALE 8.51362 -26.55602 \n", "53 4050.0 MALE 8.48095 -26.31460 \n", ".. ... ... ... ... \n", "338 4925.0 FEMALE 7.99184 -26.20538 \n", "340 4850.0 FEMALE 8.41151 -26.13832 \n", "341 5750.0 MALE 8.30166 -26.04117 \n", "342 5200.0 FEMALE 8.24246 -26.11969 \n", "343 5400.0 MALE 8.36390 -26.15531 \n", "\n", " Comments \n", "26 NaN \n", "27 NaN \n", "29 Nest never observed with full clutch. \n", "51 NaN \n", "53 NaN \n", ".. ... \n", "338 NaN \n", "340 NaN \n", "341 NaN \n", "342 NaN \n", "343 NaN \n", "\n", "[139 rows x 17 columns]" ] }, "execution_count": 56, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.query('Island == \"Biscoe\" & `Culmen Length (mm)` > 40')" ] }, { "cell_type": "code", "execution_count": 57, "id": "7e688f41-6538-4e50-a82d-d23e8e7edc47", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['Torgersen', 'Biscoe', 'Dream'], dtype=object)" ] }, "execution_count": 57, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.Island.unique()" ] }, { "cell_type": "code", "execution_count": 58, "id": "3e4d757f-4ea0-4efb-aa89-6091aebdddb8", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Island\n", "Biscoe 168\n", "Dream 124\n", "Torgersen 52\n", "Name: count, dtype: int64" ] }, "execution_count": 58, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa['Island'].value_counts()" ] }, { "cell_type": "code", "execution_count": 59, "id": "c9455d79-06f5-41ad-952e-6f321d18d58e", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Island\n", "Biscoe 45.257485\n", "Dream 44.167742\n", "Torgersen 38.950980\n", "Name: Culmen Length (mm), dtype: float64" ] }, "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dfa.groupby('Island')['Culmen Length (mm)'].mean()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.14.2" } }, "nbformat": 4, "nbformat_minor": 5 }