{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "s = pd.Series(['banana', 42])" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 banana\n", "1 42\n", "dtype: object" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "s = pd.Series(['Wes', 'Creater'], index=['person', 'who'])" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "person Wes\n", "who Creater\n", "dtype: object" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Wes'" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.loc['person']" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "'Wes'" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.iloc[0]" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "scientists=pd.DataFrame(\n", "data={'Occupation':['Chemist','Statistician'],\n", "'Born':['1920-07-25', '1876-06-13'],\n", "'Died':['1958-04-16', '1937-10-16'],\n", "'Age':[37,61]},\n", "index=['Rosaline Franklin','William Gosset'],\n", "columns=['Occupation', 'Born','Died','Age'])" ] }, { "cell_type": "code", "execution_count": 15, "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", "
OccupationBornDiedAge
Rosaline FranklinChemist1920-07-251958-04-1637
William GossetStatistician1876-06-131937-10-1661
\n", "
" ], "text/plain": [ " Occupation Born Died Age\n", "Rosaline Franklin Chemist 1920-07-25 1958-04-16 37\n", "William Gosset Statistician 1876-06-13 1937-10-16 61" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "scientists = pd.read_csv('../data/scientists.csv')" ] }, { "cell_type": "code", "execution_count": 17, "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", "
NameBornDiedAgeOccupation
0Rosaline Franklin1920-07-251958-04-1637Chemist
1William Gosset1876-06-131937-10-1661Statistician
2Florence Nightingale1820-05-121910-08-1390Nurse
3Marie Curie1867-11-071934-07-0466Chemist
4Rachel Carson1907-05-271964-04-1456Biologist
5John Snow1813-03-151858-06-1645Physician
6Alan Turing1912-06-231954-06-0741Computer Scientist
7Johann Gauss1777-04-301855-02-2377Mathematician
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist\n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician\n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse\n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist\n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist\n", "5 John Snow 1813-03-15 1858-06-16 45 Physician\n", "6 Alan Turing 1912-06-23 1954-06-07 41 Computer Scientist\n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "ages = scientists['Age']" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 37\n", "1 61\n", "2 90\n", "3 66\n", "4 56\n", "5 45\n", "6 41\n", "7 77\n", "Name: Age, dtype: int64" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 37\n", "1 61\n", "2 90\n", "3 66\n", "4 56\n", "5 45\n", "6 41\n", "7 77\n", "Name: Age, dtype: int64" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages = scientists.Age\n", "ages" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(8, 5)" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# if shape is a column name you *have* to use square brackets\n", "# scientists['shape']" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "pandas.core.series.Series" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "type(ages)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "59.125" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages.mean()" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(8,)" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages.shape" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "37" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages.min()" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "count 8.000000\n", "mean 59.125000\n", "std 18.325918\n", "min 37.000000\n", "25% 44.000000\n", "50% 58.500000\n", "75% 68.750000\n", "max 90.000000\n", "Name: Age, dtype: float64" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages.describe()" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1 61\n", "2 90\n", "3 66\n", "7 77\n", "Name: Age, dtype: int64" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages[ages > ages.mean()]" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "2 90\n", "7 77\n", "Name: Age, dtype: int64" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages[(ages > ages.mean()) & (ages > 75)]" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "ename": "TypeError", "evalue": "cannot compare a dtyped [int64] array with a scalar of type [bool]", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\pandas\\core\\ops.py\u001b[0m in \u001b[0;36mna_op\u001b[1;34m(x, y)\u001b[0m\n\u001b[0;32m 882\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 883\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 884\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\pandas\\core\\ops.py\u001b[0m in \u001b[0;36m\u001b[1;34m(x, y)\u001b[0m\n\u001b[0;32m 128\u001b[0m \u001b[0mxor\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbool_method\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0moperator\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mxor\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnames\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'xor'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'^'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 129\u001b[1;33m rand_=bool_method(lambda x, y: operator.and_(y, x),\n\u001b[0m\u001b[0;32m 130\u001b[0m names('rand_'), op('&')),\n", "\u001b[1;31mTypeError\u001b[0m: ufunc 'bitwise_and' not supported for the input types, and the inputs could not be safely coerced to any supported types according to the casting rule ''safe''", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\pandas\\core\\ops.py\u001b[0m in \u001b[0;36mna_op\u001b[1;34m(x, y)\u001b[0m\n\u001b[0;32m 900\u001b[0m \u001b[0my\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbool\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0my\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 901\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscalar_binop\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0my\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 902\u001b[0m \u001b[1;32mexcept\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32mpandas\\_libs\\lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.scalar_binop\u001b[1;34m()\u001b[0m\n", "\u001b[1;31mValueError\u001b[0m: Buffer dtype mismatch, expected 'Python object' but got 'long long'", "\nDuring handling of the above exception, another exception occurred:\n", "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mages\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mages\u001b[0m \u001b[1;33m>\u001b[0m \u001b[0mages\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m&\u001b[0m \u001b[0mages\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m75\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\pandas\\core\\ops.py\u001b[0m in \u001b[0;36mwrapper\u001b[1;34m(self, other)\u001b[0m\n\u001b[0;32m 933\u001b[0m is_integer_dtype(np.asarray(other)) else fill_bool)\n\u001b[0;32m 934\u001b[0m return filler(self._constructor(\n\u001b[1;32m--> 935\u001b[1;33m \u001b[0mna_op\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mother\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 936\u001b[0m index=self.index)).__finalize__(self)\n\u001b[0;32m 937\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\pandas\\core\\ops.py\u001b[0m in \u001b[0;36mna_op\u001b[1;34m(x, y)\u001b[0m\n\u001b[0;32m 903\u001b[0m raise TypeError(\"cannot compare a dtyped [{0}] array with \"\n\u001b[0;32m 904\u001b[0m \"a scalar of type [{1}]\".format(\n\u001b[1;32m--> 905\u001b[1;33m x.dtype, type(y).__name__))\n\u001b[0m\u001b[0;32m 906\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 907\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mTypeError\u001b[0m: cannot compare a dtyped [int64] array with a scalar of type [bool]" ] } ], "source": [ "ages[ages > ages.mean() & ages > 75]" ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "1 61\n", "3 66\n", "Name: Age, dtype: int64" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages[(ages > ages.mean()) & ~(ages > 75)]" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "count 8.000000\n", "mean 59.125000\n", "std 18.325918\n", "min 37.000000\n", "25% 44.000000\n", "50% 58.500000\n", "75% 68.750000\n", "max 90.000000\n", "Name: Age, dtype: float64" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages.describe()" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 137\n", "1 161\n", "2 190\n", "3 166\n", "4 156\n", "5 145\n", "6 141\n", "7 177\n", "Name: Age, dtype: int64" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ages + 100" ] }, { "cell_type": "code", "execution_count": 35, "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", "
NameBornDiedAgeOccupation
0Rosaline Franklin1920-07-251958-04-1637Chemist
1William Gosset1876-06-131937-10-1661Statistician
2Florence Nightingale1820-05-121910-08-1390Nurse
3Marie Curie1867-11-071934-07-0466Chemist
4Rachel Carson1907-05-271964-04-1456Biologist
5John Snow1813-03-151858-06-1645Physician
6Alan Turing1912-06-231954-06-0741Computer Scientist
7Johann Gauss1777-04-301855-02-2377Mathematician
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist\n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician\n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse\n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist\n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist\n", "5 John Snow 1813-03-15 1858-06-16 45 Physician\n", "6 Alan Turing 1912-06-23 1954-06-07 41 Computer Scientist\n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 36, "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", "
NameBornDiedAgeOccupation
1William Gosset1876-06-131937-10-1661Statistician
2Florence Nightingale1820-05-121910-08-1390Nurse
3Marie Curie1867-11-071934-07-0466Chemist
7Johann Gauss1777-04-301855-02-2377Mathematician
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation\n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician\n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse\n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist\n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists[scientists['Age'] > scientists['Age'].mean()]" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 False\n", "1 True\n", "2 True\n", "3 True\n", "4 False\n", "5 False\n", "6 False\n", "7 True\n", "Name: Age, dtype: bool" ] }, "execution_count": 37, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists['Age'] > scientists['Age'].mean()" ] }, { "cell_type": "code", "execution_count": 40, "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", "
NameBornDiedAgeOccupation
0Rosaline Franklin1920-07-251958-04-1637Chemist
1William Gosset1876-06-131937-10-1661Statistician
2Florence Nightingale1820-05-121910-08-1390Nurse
3Marie Curie1867-11-071934-07-0466Chemist
4Rachel Carson1907-05-271964-04-1456Biologist
5John Snow1813-03-151858-06-1645Physician
6Alan Turing1912-06-231954-06-0741Computer Scientist
7Johann Gauss1777-04-301855-02-2377Mathematician
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist\n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician\n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse\n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist\n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist\n", "5 John Snow 1813-03-15 1858-06-16 45 Physician\n", "6 Alan Turing 1912-06-23 1954-06-07 41 Computer Scientist\n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Name object\n", "Born object\n", "Died object\n", "Age int64\n", "Occupation object\n", "dtype: object" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists.dtypes" ] }, { "cell_type": "code", "execution_count": 44, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "# strftime\n", "born_datetime = pd.to_datetime(scientists['Born'], format='%Y-%m-%d')" ] }, { "cell_type": "code", "execution_count": 43, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "pd.to_datetime?" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 1920-07-25\n", "1 1876-06-13\n", "2 1820-05-12\n", "3 1867-11-07\n", "4 1907-05-27\n", "5 1813-03-15\n", "6 1912-06-23\n", "7 1777-04-30\n", "Name: Born, dtype: datetime64[ns]" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "born_datetime" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [], "source": [ "scientists['born_dt'] = born_datetime" ] }, { "cell_type": "code", "execution_count": 49, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "# same as above\n", "scientists['born_dt'] = pd.to_datetime(scientists['Born'], format='%Y-%m-%d')" ] }, { "cell_type": "code", "execution_count": 50, "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", "
NameBornDiedAgeOccupationborn_dt
0Rosaline Franklin1920-07-251958-04-1637Chemist1920-07-25
1William Gosset1876-06-131937-10-1661Statistician1876-06-13
2Florence Nightingale1820-05-121910-08-1390Nurse1820-05-12
3Marie Curie1867-11-071934-07-0466Chemist1867-11-07
4Rachel Carson1907-05-271964-04-1456Biologist1907-05-27
5John Snow1813-03-151858-06-1645Physician1813-03-15
6Alan Turing1912-06-231954-06-0741Computer Scientist1912-06-23
7Johann Gauss1777-04-301855-02-2377Mathematician1777-04-30
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation \\\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist \n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician \n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse \n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist \n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist \n", "5 John Snow 1813-03-15 1858-06-16 45 Physician \n", "6 Alan Turing 1912-06-23 1954-06-07 41 Computer Scientist \n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician \n", "\n", " born_dt \n", "0 1920-07-25 \n", "1 1876-06-13 \n", "2 1820-05-12 \n", "3 1867-11-07 \n", "4 1907-05-27 \n", "5 1813-03-15 \n", "6 1912-06-23 \n", "7 1777-04-30 " ] }, "execution_count": 50, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 51, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 8 entries, 0 to 7\n", "Data columns (total 6 columns):\n", "Name 8 non-null object\n", "Born 8 non-null object\n", "Died 8 non-null object\n", "Age 8 non-null int64\n", "Occupation 8 non-null object\n", "born_dt 8 non-null datetime64[ns]\n", "dtypes: datetime64[ns](1), int64(1), object(4)\n", "memory usage: 464.0+ bytes\n" ] } ], "source": [ "scientists.info()" ] }, { "cell_type": "code", "execution_count": 53, "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", "
NameBornDiedAgeOccupationborn_dtdied_dt
0Rosaline Franklin1920-07-251958-04-1637Chemist1920-07-251958-04-16
1William Gosset1876-06-131937-10-1661Statistician1876-06-131937-10-16
2Florence Nightingale1820-05-121910-08-1390Nurse1820-05-121910-08-13
3Marie Curie1867-11-071934-07-0466Chemist1867-11-071934-07-04
4Rachel Carson1907-05-271964-04-1456Biologist1907-05-271964-04-14
5John Snow1813-03-151858-06-1645Physician1813-03-151858-06-16
6Alan Turing1912-06-231954-06-0741Computer Scientist1912-06-231954-06-07
7Johann Gauss1777-04-301855-02-2377Mathematician1777-04-301855-02-23
\n", "
" ], "text/plain": [ " Name Born Died Age Occupation \\\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist \n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician \n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse \n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist \n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist \n", "5 John Snow 1813-03-15 1858-06-16 45 Physician \n", "6 Alan Turing 1912-06-23 1954-06-07 41 Computer Scientist \n", "7 Johann Gauss 1777-04-30 1855-02-23 77 Mathematician \n", "\n", " born_dt died_dt \n", "0 1920-07-25 1958-04-16 \n", "1 1876-06-13 1937-10-16 \n", "2 1820-05-12 1910-08-13 \n", "3 1867-11-07 1934-07-04 \n", "4 1907-05-27 1964-04-14 \n", "5 1813-03-15 1858-06-16 \n", "6 1912-06-23 1954-06-07 \n", "7 1777-04-30 1855-02-23 " ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists['died_dt'] = pd.to_datetime(scientists['Died'], format='%Y-%m-%d')\n", "scientists" ] }, { "cell_type": "code", "execution_count": 54, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [ "scientists = scientists.drop(['Born', 'Died'], axis=1)" ] }, { "cell_type": "code", "execution_count": 55, "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NameAgeOccupationborn_dtdied_dt
0Rosaline Franklin37Chemist1920-07-251958-04-16
1William Gosset61Statistician1876-06-131937-10-16
2Florence Nightingale90Nurse1820-05-121910-08-13
3Marie Curie66Chemist1867-11-071934-07-04
4Rachel Carson56Biologist1907-05-271964-04-14
5John Snow45Physician1813-03-151858-06-16
6Alan Turing41Computer Scientist1912-06-231954-06-07
7Johann Gauss77Mathematician1777-04-301855-02-23
\n", "
" ], "text/plain": [ " Name Age Occupation born_dt died_dt\n", "0 Rosaline Franklin 37 Chemist 1920-07-25 1958-04-16\n", "1 William Gosset 61 Statistician 1876-06-13 1937-10-16\n", "2 Florence Nightingale 90 Nurse 1820-05-12 1910-08-13\n", "3 Marie Curie 66 Chemist 1867-11-07 1934-07-04\n", "4 Rachel Carson 56 Biologist 1907-05-27 1964-04-14\n", "5 John Snow 45 Physician 1813-03-15 1858-06-16\n", "6 Alan Turing 41 Computer Scientist 1912-06-23 1954-06-07\n", "7 Johann Gauss 77 Mathematician 1777-04-30 1855-02-23" ] }, "execution_count": 55, "metadata": {}, "output_type": "execute_result" } ], "source": [ "scientists" ] }, { "cell_type": "code", "execution_count": 59, "metadata": {}, "outputs": [], "source": [ "scientists.to_csv('scientists_clean.csv', index=False)" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Name Born Died Age Occupation\n", "0 Rosaline Franklin 1920-07-25 1958-04-16 37 Chemist\n", "1 William Gosset 1876-06-13 1937-10-16 61 Statistician\n", "2 Florence Nightingale 1820-05-12 1910-08-13 90 Nurse\n", "3 Marie Curie 1867-11-07 1934-07-04 66 Chemist\n", "4 Rachel Carson 1907-05-27 1964-04-14 56 Biologist\n", " Name Age Occupation\n", "0 Rosaline Franklin 37 Chemist\n", "1 William Gosset 61 Statistician\n", "2 Florence Nightingale 90 Nurse\n", "3 Marie Curie 66 Chemist\n", "4 Rachel Carson 56 Biologist\n" ] } ], "source": [ "# drop column full example\n", "scientists = pd.read_csv('../data/scientists.csv', sep=',') # sep=',' is the default\n", "scientists = pd.read_csv('../data/scientists.csv')\n", "scientists = pd.read_csv('../data/scientists.csv', ',') # using positional argument passing for sep\n", "print(scientists.head())\n", "\n", "# remember you need to re-assign the 'dropped' dataframe\n", "scientists = scientists.drop(['Born', 'Died'], axis=1)\n", "print(scientists.head())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true, "jupyter": { "outputs_hidden": true } }, "outputs": [], "source": [] } ], "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": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 4 }