diff --git a/practice/PD1.ipynb b/practice/PD1.ipynb new file mode 100644 index 0000000..2ea9bc9 --- /dev/null +++ b/practice/PD1.ipynb @@ -0,0 +1,206 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "id": "681405ed", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "4320e7b8", + "metadata": {}, + "outputs": [], + "source": [ + "\"\"\"\n", + "#DataFrame:\n", + " main data struct in Pandas\n", + " a table w/many funcs.\n", + "\n", + "\"\"\"\n", + "\n", + "df=pd.DataFrame([[1,2,3],\n", + " [4,5,6],\n", + " [7,8,9]], \n", + " columns=[\"A\", \"B\", \"C\"],#Adds labels to the columns\n", + " index=[\"a\", \"b\", \"c\"]) #labels to rows" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "6f9159ef", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " A B C\n", + "a 1 2 3\n", + "b 4 5 6\n", + "c 7 8 9\n" + ] + } + ], + "source": [ + "print(df.head())#first five rows (here there are only three)\n", + "\n", + "\"\"\"\n", + "Outout w/o columns & indices defnd.:\n", + " 0 1 2\n", + "0 1 2 3\n", + "1 4 5 6\n", + "2 7 8 9\n", + "\n", + "Outout w/columns defnd.:\n", + " A B C\n", + "0 1 2 3\n", + "1 4 5 6\n", + "2 7 8 9\n", + "\n", + "Outout w/indices defnd.:\n", + " A B C\n", + "a 1 2 3\n", + "b 4 5 6\n", + "c 7 8 9\n", + "\n", + "\"\"\"" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "f34c9950", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "Index: 3 entries, a to c\n", + "Data columns (total 3 columns):\n", + " # Column Non-Null Count Dtype\n", + "--- ------ -------------- -----\n", + " 0 A 3 non-null int64\n", + " 1 B 3 non-null int64\n", + " 2 C 3 non-null int64\n", + "dtypes: int64(3)\n", + "memory usage: 96.0+ bytes\n", + "None\n" + ] + } + ], + "source": [ + "print(df.info())" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "0a140f8c", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + " A B C\n", + "count 3.0 3.0 3.0\n", + "mean 4.0 5.0 6.0\n", + "std 3.0 3.0 3.0\n", + "min 1.0 2.0 3.0\n", + "25% 2.5 3.5 4.5\n", + "50% 4.0 5.0 6.0\n", + "75% 5.5 6.5 7.5\n", + "max 7.0 8.0 9.0\n" + ] + } + ], + "source": [ + "print(f\"\\n{df.describe()}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "905150e7", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "A 3\n", + "B 3\n", + "C 3\n", + "dtype: int64\n", + "\n", + "3\n" + ] + } + ], + "source": [ + "print(df.nunique())#entire DF\n", + "print(f\"\\n{df[\"A\"].nunique()}\")#partclr col" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "42e927bf", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(3, 3)" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.shape" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "78326e0f", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.13.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/practice/PD2.ipynb b/practice/PD2.ipynb new file mode 100644 index 0000000..e7b335f --- /dev/null +++ b/practice/PD2.ipynb @@ -0,0 +1,553 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 28, + "id": "c9f0d034", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "id": "adbb0c2f", + "metadata": {}, + "outputs": [], + "source": [ + "coffeeDF=pd.read_csv('coffeeDF.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "4c453243", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + " Day Coffee Units Sold\n", + "0 Monday Espresso 23\n", + "1 Monday Latte 34\n", + "2 Tuesday Espresso 34\n", + "3 Tuesday Latte 45\n", + "4 Wednesday Espresso 56\n", + "\n", + "RangeIndex: 14 entries, 0 to 13\n", + "Data columns (total 3 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 Day 14 non-null object\n", + " 1 Coffee 14 non-null object\n", + " 2 Units Sold 14 non-null int64 \n", + "dtypes: int64(1), object(2)\n", + "memory usage: 468.0+ bytes\n", + "\n", + "None\n", + "\n", + " Units Sold\n", + "count 14.000000\n", + "mean 53.071429\n", + "std 26.042759\n", + "min 23.000000\n", + "25% 32.500000\n", + "50% 45.000000\n", + "75% 64.250000\n", + "max 100.000000\n", + "\n", + "(14, 3)\n" + ] + } + ], + "source": [ + "print(f\"\\n{coffeeDF.head()}\")\n", + "print(f\"\\n{coffeeDF.info()}\")\n", + "print(f\"\\n{coffeeDF.describe()}\")\n", + "print(f\"\\n{coffeeDF.shape}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "a0c258be", + "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", + "
DayCoffeeUnits Sold
10SaturdayEspresso32
12SundayEspresso100
11SaturdayLatte56
6ThursdayEspresso45
4WednesdayEspresso56
7ThursdayLatte67
13SundayLatte98
3TuesdayLatte45
5WednesdayLatte32
0MondayEspresso23
\n", + "
" + ], + "text/plain": [ + " Day Coffee Units Sold\n", + "10 Saturday Espresso 32\n", + "12 Sunday Espresso 100\n", + "11 Saturday Latte 56\n", + "6 Thursday Espresso 45\n", + "4 Wednesday Espresso 56\n", + "7 Thursday Latte 67\n", + "13 Sunday Latte 98\n", + "3 Tuesday Latte 45\n", + "5 Wednesday Latte 32\n", + "0 Monday Espresso 23" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# coffeeDF.tail()#deflt. param is 5\n", + "coffeeDF.tail(7)\n", + "\n", + "coffeeDF.sample(10)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "4f0fe2d3", + "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", + "
DayCoffeeUnits Sold
0MondayEspresso23
1MondayLatte34
2TuesdayEspresso34
3TuesdayLatte45
4WednesdayEspresso56
5WednesdayLatte32
6ThursdayEspresso45
7ThursdayLatte67
8FridayEspresso89
9FridayLatte32
10SaturdayEspresso32
11SaturdayLatte56
12SundayEspresso100
13SundayLatte98
\n", + "
" + ], + "text/plain": [ + " Day Coffee Units Sold\n", + "0 Monday Espresso 23\n", + "1 Monday Latte 34\n", + "2 Tuesday Espresso 34\n", + "3 Tuesday Latte 45\n", + "4 Wednesday Espresso 56\n", + "5 Wednesday Latte 32\n", + "6 Thursday Espresso 45\n", + "7 Thursday Latte 67\n", + "8 Friday Espresso 89\n", + "9 Friday Latte 32\n", + "10 Saturday Espresso 32\n", + "11 Saturday Latte 56\n", + "12 Sunday Espresso 100\n", + "13 Sunday Latte 98" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#loc & iloc\n", + "\n", + "#loc: filter by rows & cols of the DF\n", + "# coffeeDF.loc[row, col]\n", + "# lenDF=len(coffeeDF.loc[0:])\n", + "# coffeeDF.loc[lenDF:-1]\n", + "coffeeDF.loc[:, \"Coffee\"]\n", + "# print(lenDF)\n", + "\n", + "\n", + "#iloc\n", + "coffeeDF.iloc[0:,0:]\n", + "# coffeeDF.iloc[0:,0:1]\n", + "# coffeeDF.iloc[0:,0:2]" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "id": "c420e818", + "metadata": {}, + "outputs": [], + "source": [ + "#at & iat\n", + "# coffeeDF.at[1, \"Coffee\"]\n", + "# coffeeDF.iat[1, 1]\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "c431ee6b", + "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", + "
DayCoffeeUnits Sold
12SundayEspresso100
13SundayLatte98
8FridayEspresso89
7ThursdayLatte67
11SaturdayLatte56
4WednesdayEspresso56
3TuesdayLatte45
6ThursdayEspresso45
1MondayLatte34
2TuesdayEspresso34
5WednesdayLatte32
9FridayLatte32
10SaturdayEspresso32
0MondayEspresso23
\n", + "
" + ], + "text/plain": [ + " Day Coffee Units Sold\n", + "12 Sunday Espresso 100\n", + "13 Sunday Latte 98\n", + "8 Friday Espresso 89\n", + "7 Thursday Latte 67\n", + "11 Saturday Latte 56\n", + "4 Wednesday Espresso 56\n", + "3 Tuesday Latte 45\n", + "6 Thursday Espresso 45\n", + "1 Monday Latte 34\n", + "2 Tuesday Espresso 34\n", + "5 Wednesday Latte 32\n", + "9 Friday Latte 32\n", + "10 Saturday Espresso 32\n", + "0 Monday Espresso 23" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#sorting\n", + "\n", + "# coffeeDF.sort_values(\"Units Sold\", ascending=True)#default\n", + "# coffeeDF.sort_values(\"Units Sold\", ascending=False)\n", + "\n", + "coffeeDF.sort_values([\"Units Sold\", \"Coffee\"], ascending=False) #will first sort by param. 1, then 2, & bcz \"Coffee\" vars are alphabetic, it eill sort alphabetically\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "9139d811", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.13.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/practice/PD3.ipynb b/practice/PD3.ipynb new file mode 100644 index 0000000..0479c03 --- /dev/null +++ b/practice/PD3.ipynb @@ -0,0 +1,1090 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "id": "9f85e06d", + "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", + "
athlete_idnameborn_dateborn_cityborn_regionborn_countryNOCheight_cmweight_kgdied_date
01Jean-François Blanchy1886-12-12BordeauxGirondeFRAFranceNaNNaN1960-10-02
12Arnaud Boetsch1969-04-01MeulanYvelinesFRAFrance183.076.0NaN
23Jean Borotra1898-08-13BiarritzPyrénées-AtlantiquesFRAFrance183.076.01994-07-17
34Jacques Brugnon1895-05-11Paris VIIIeParisFRAFrance168.064.01978-03-20
45Albert Canet1878-04-17WandsworthEnglandGBRFranceNaNNaN1930-07-25
\n", + "
" + ], + "text/plain": [ + " athlete_id name born_date born_city \\\n", + "0 1 Jean-François Blanchy 1886-12-12 Bordeaux \n", + "1 2 Arnaud Boetsch 1969-04-01 Meulan \n", + "2 3 Jean Borotra 1898-08-13 Biarritz \n", + "3 4 Jacques Brugnon 1895-05-11 Paris VIIIe \n", + "4 5 Albert Canet 1878-04-17 Wandsworth \n", + "\n", + " born_region born_country NOC height_cm weight_kg died_date \n", + "0 Gironde FRA France NaN NaN 1960-10-02 \n", + "1 Yvelines FRA France 183.0 76.0 NaN \n", + "2 Pyrénées-Atlantiques FRA France 183.0 76.0 1994-07-17 \n", + "3 Paris FRA France 168.0 64.0 1978-03-20 \n", + "4 England GBR France NaN NaN 1930-07-25 " + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "\n", + "bios=pd.read_csv(\"D:\\\\Documents\\\\Programming\\\\Languages\\\\Python\\\\Python Tutorials\\\\Python-Libraries\\\\Pandas\\\\pandas-tutorial\\\\data\\\\bios.csv\")\n", + "\n", + "bios.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "d554631e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 1886-12-12\n", + "1 1969-04-01\n", + "2 1898-08-13\n", + "3 1895-05-11\n", + "4 1878-04-17\n", + "5 1970-01-13\n", + "6 1969-11-27\n", + "Name: born_date, dtype: object" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bios.loc[0:6, \"born_date\"]" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "da4c6a77", + "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", + "
athlete_idnameborn_dateborn_cityborn_regionborn_countryNOCheight_cmweight_kgdied_date
6245162914William Martin1828-10-25RouenSeine-MaritimeFRAFranceNaNNaN1905-02-25
6310963579Ferdinand de Schlatter1831-02-14Paris IVeParisFRAFranceNaNNaN1907-07-04
1183611898Louis, Comte du Douet de Graville1831-02-27BernièresSeine-MaritimeFRAFranceNaNNaN1912-10-12
22352245Thomas Scott1833-01-03WarrenOhioUSAUnited StatesNaNNaN1911-06-23
22202230Samuel Duvall1836-03-11LibertyIndianaUSAUnited StatesNaNNaN1908-09-26
.................................
126484128839Werner FehrNaNNaNNaNNaNSwitzerlandNaNNaN1943-09-08
135275138438Aleko MulosNaNNaNNaNNaNTürkiyeNaNNaNNaN
135280138443Louis LéstienneNaNNaNNaNNaNFranceNaNNaNNaN
144129147802René Van DammeNaNNaNNaNNaNBelgiumNaNNaNNaN
144132147805Raphael de LigneNaNNaNNaNNaNBelgiumNaNNaNNaN
\n", + "

145500 rows × 10 columns

\n", + "
" + ], + "text/plain": [ + " athlete_id name born_date born_city \\\n", + "62451 62914 William Martin 1828-10-25 Rouen \n", + "63109 63579 Ferdinand de Schlatter 1831-02-14 Paris IVe \n", + "11836 11898 Louis, Comte du Douet de Graville 1831-02-27 Bernières \n", + "2235 2245 Thomas Scott 1833-01-03 Warren \n", + "2220 2230 Samuel Duvall 1836-03-11 Liberty \n", + "... ... ... ... ... \n", + "126484 128839 Werner Fehr NaN NaN \n", + "135275 138438 Aleko Mulos NaN NaN \n", + "135280 138443 Louis Léstienne NaN NaN \n", + "144129 147802 René Van Damme NaN NaN \n", + "144132 147805 Raphael de Ligne NaN NaN \n", + "\n", + " born_region born_country NOC height_cm weight_kg \\\n", + "62451 Seine-Maritime FRA France NaN NaN \n", + "63109 Paris FRA France NaN NaN \n", + "11836 Seine-Maritime FRA France NaN NaN \n", + "2235 Ohio USA United States NaN NaN \n", + "2220 Indiana USA United States NaN NaN \n", + "... ... ... ... ... ... \n", + "126484 NaN NaN Switzerland NaN NaN \n", + "135275 NaN NaN Türkiye NaN NaN \n", + "135280 NaN NaN France NaN NaN \n", + "144129 NaN NaN Belgium NaN NaN \n", + "144132 NaN NaN Belgium NaN NaN \n", + "\n", + " died_date \n", + "62451 1905-02-25 \n", + "63109 1907-07-04 \n", + "11836 1912-10-12 \n", + "2235 1911-06-23 \n", + "2220 1908-09-26 \n", + "... ... \n", + "126484 1943-09-08 \n", + "135275 NaN \n", + "135280 NaN \n", + "144129 NaN \n", + "144132 NaN \n", + "\n", + "[145500 rows x 10 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bios.sort_values(\"born_date\")" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "2175bbe5", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(145500, 10)" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "bios.shape\n" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "95aaf11c", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "RangeIndex: 145500 entries, 0 to 145499\n", + "Data columns (total 10 columns):\n", + " # Column Non-Null Count Dtype \n", + "--- ------ -------------- ----- \n", + " 0 athlete_id 145500 non-null int64 \n", + " 1 name 145500 non-null object \n", + " 2 born_date 143693 non-null object \n", + " 3 born_city 110908 non-null object \n", + " 4 born_region 110908 non-null object \n", + " 5 born_country 110908 non-null object \n", + " 6 NOC 145499 non-null object \n", + " 7 height_cm 106651 non-null float64\n", + " 8 weight_kg 102070 non-null float64\n", + " 9 died_date 33940 non-null object \n", + "dtypes: float64(2), int64(1), object(7)\n", + "memory usage: 11.1+ MB\n" + ] + } + ], + "source": [ + "bios.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "fc5d4926", + "metadata": {}, + "outputs": [], + "source": [ + "# bios.loc[bios[\"name\"].str.contains(\"Manas\")]\n", + "# bios.loc[bios[\"born_country\"]==\"IND\" & bios[\"NOC\"]==\"India\"] wrong\n", + "# bios[bios[\"born_country\"]==\"IND\" & bios[\"NOC\"]==\"India\"] wrong" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "5ea7fcf5", + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
athlete_idnameborn_dateborn_cityborn_regionborn_countryNOCheight_cmweight_kgdied_date
279280Ali Athar Fyzee1883-08-28MumbaiMaharashtraINDIndiaNaNNaN1963-11-03
285286Kamlesh Mehta1960-05-01MumbaiMaharashtraINDIndiaNaNNaNNaN
1292312994Frank Weldon1913-08-02MumbaiMaharashtraINDGreat Britain175.066.01993-09-21
1459314691Bapoo Malcolm1912-12-12MumbaiMaharashtraINDIndiaNaNNaN1982-01-19
1870118829Richard Norris1931-12-10MumbaiMaharashtraINDGreat BritainNaNNaN2012-08-25
1872818856Frederick Scott1932-11-29MumbaiMaharashtraINDGreat BritainNaNNaN2017-01-01
1901819151Ashish Kumar Ballal1970-10-08MumbaiMaharashtraINDIndiaNaNNaNNaN
2322623402Rolf Edling1943-11-30MumbaiMaharashtraINDSweden196.091.0NaN
3323733489Cawas Billimoria1962-10-25MumbaiMaharashtraINDIndiaNaNNaNNaN
4705047400Peter Squires1936-05-28MumbaiMaharashtraINDGreat Britain168.063.02011-09-16
4792448276Shrichand Bajaj1933-10-01MumbaiMaharashtraINDIndiaNaNNaN2005-07-20
4793048282Isaac Mansoor1929-05-30MumbaiMaharashtraINDIndiaNaNNaN2006-01-01
5384754233David Sopher1929-02-01MumbaiMaharashtraINDIndiaNaNNaN2019-02-14
5604456442Rory Barrett1945-12-31MumbaiMaharashtraINDNew Zealand185.0110.0NaN
6202362479Harry Jefferson1849-03-09MumbaiMaharashtraINDGreat BritainNaNNaN1918-06-23
6851769034Launceston Elliot1874-06-09MumbaiMaharashtraINDGreat Britain188.0102.01930-08-08
6960970130Manisha Malhotra1976-09-19MumbaiMaharashtraINDIndiaNaNNaNNaN
7087971411Eddie Sequeira1942-02-06MumbaiMaharashtraINDIndia172.054.0NaN
7208472630Shoichiro Takenaka1912-09-30MumbaiMaharashtraINDJapan158.046.01997-04-04
8208982742Aparna Popat1978-01-18MumbaiMaharashtraINDIndia160.065.0NaN
8364484307John Boyagis1928-01-26MumbaiMaharashtraINDGreat BritainNaNNaN2020-07-22
9093791661Robin D'Abreo1975-03-03MumbaiMaharashtraINDCanada178.066.0NaN
9097891704Jude Menezes1971-08-05MumbaiMaharashtraINDIndia172.075.0NaN
9233793077Anjali Vedpathak-Bhagwat1969-12-05MumbaiMaharashtraINDIndia165.053.0NaN
103745104738Deepali Deshpande1969-08-03MumbaiMaharashtraINDIndia159.054.0NaN
107864109002Viren Rasquinha1980-09-13MumbaiMaharashtraINDIndia170.065.0NaN
119636121462Mayookha Johny1988-04-09MumbaiMaharashtraINDIndia174.058.0NaN
128066130572Ayonika Paul1992-09-23MumbaiMaharashtraINDIndia174.074.0NaN
130375133059Keegan Pereira1991-09-08MumbaiMaharashtraINDCanada166.059.0NaN
131627134441Devindar Walmiki1992-05-28MumbaiMaharashtraINDIndia178.069.0NaN
134610137691Anice Das1985-12-31MumbaiMaharashtraINDNetherlands170.065.0NaN
\n", + "
" + ], + "text/plain": [ + " athlete_id name born_date born_city \\\n", + "279 280 Ali Athar Fyzee 1883-08-28 Mumbai \n", + "285 286 Kamlesh Mehta 1960-05-01 Mumbai \n", + "12923 12994 Frank Weldon 1913-08-02 Mumbai \n", + "14593 14691 Bapoo Malcolm 1912-12-12 Mumbai \n", + "18701 18829 Richard Norris 1931-12-10 Mumbai \n", + "18728 18856 Frederick Scott 1932-11-29 Mumbai \n", + "19018 19151 Ashish Kumar Ballal 1970-10-08 Mumbai \n", + "23226 23402 Rolf Edling 1943-11-30 Mumbai \n", + "33237 33489 Cawas Billimoria 1962-10-25 Mumbai \n", + "47050 47400 Peter Squires 1936-05-28 Mumbai \n", + "47924 48276 Shrichand Bajaj 1933-10-01 Mumbai \n", + "47930 48282 Isaac Mansoor 1929-05-30 Mumbai \n", + "53847 54233 David Sopher 1929-02-01 Mumbai \n", + "56044 56442 Rory Barrett 1945-12-31 Mumbai \n", + "62023 62479 Harry Jefferson 1849-03-09 Mumbai \n", + "68517 69034 Launceston Elliot 1874-06-09 Mumbai \n", + "69609 70130 Manisha Malhotra 1976-09-19 Mumbai \n", + "70879 71411 Eddie Sequeira 1942-02-06 Mumbai \n", + "72084 72630 Shoichiro Takenaka 1912-09-30 Mumbai \n", + "82089 82742 Aparna Popat 1978-01-18 Mumbai \n", + "83644 84307 John Boyagis 1928-01-26 Mumbai \n", + "90937 91661 Robin D'Abreo 1975-03-03 Mumbai \n", + "90978 91704 Jude Menezes 1971-08-05 Mumbai \n", + "92337 93077 Anjali Vedpathak-Bhagwat 1969-12-05 Mumbai \n", + "103745 104738 Deepali Deshpande 1969-08-03 Mumbai \n", + "107864 109002 Viren Rasquinha 1980-09-13 Mumbai \n", + "119636 121462 Mayookha Johny 1988-04-09 Mumbai \n", + "128066 130572 Ayonika Paul 1992-09-23 Mumbai \n", + "130375 133059 Keegan Pereira 1991-09-08 Mumbai \n", + "131627 134441 Devindar Walmiki 1992-05-28 Mumbai \n", + "134610 137691 Anice Das 1985-12-31 Mumbai \n", + "\n", + " born_region born_country NOC height_cm weight_kg \\\n", + "279 Maharashtra IND India NaN NaN \n", + "285 Maharashtra IND India NaN NaN \n", + "12923 Maharashtra IND Great Britain 175.0 66.0 \n", + "14593 Maharashtra IND India NaN NaN \n", + "18701 Maharashtra IND Great Britain NaN NaN \n", + "18728 Maharashtra IND Great Britain NaN NaN \n", + "19018 Maharashtra IND India NaN NaN \n", + "23226 Maharashtra IND Sweden 196.0 91.0 \n", + "33237 Maharashtra IND India NaN NaN \n", + "47050 Maharashtra IND Great Britain 168.0 63.0 \n", + "47924 Maharashtra IND India NaN NaN \n", + "47930 Maharashtra IND India NaN NaN \n", + "53847 Maharashtra IND India NaN NaN \n", + "56044 Maharashtra IND New Zealand 185.0 110.0 \n", + "62023 Maharashtra IND Great Britain NaN NaN \n", + "68517 Maharashtra IND Great Britain 188.0 102.0 \n", + "69609 Maharashtra IND India NaN NaN \n", + "70879 Maharashtra IND India 172.0 54.0 \n", + "72084 Maharashtra IND Japan 158.0 46.0 \n", + "82089 Maharashtra IND India 160.0 65.0 \n", + "83644 Maharashtra IND Great Britain NaN NaN \n", + "90937 Maharashtra IND Canada 178.0 66.0 \n", + "90978 Maharashtra IND India 172.0 75.0 \n", + "92337 Maharashtra IND India 165.0 53.0 \n", + "103745 Maharashtra IND India 159.0 54.0 \n", + "107864 Maharashtra IND India 170.0 65.0 \n", + "119636 Maharashtra IND India 174.0 58.0 \n", + "128066 Maharashtra IND India 174.0 74.0 \n", + "130375 Maharashtra IND Canada 166.0 59.0 \n", + "131627 Maharashtra IND India 178.0 69.0 \n", + "134610 Maharashtra IND Netherlands 170.0 65.0 \n", + "\n", + " died_date \n", + "279 1963-11-03 \n", + "285 NaN \n", + "12923 1993-09-21 \n", + "14593 1982-01-19 \n", + "18701 2012-08-25 \n", + "18728 2017-01-01 \n", + "19018 NaN \n", + "23226 NaN \n", + "33237 NaN \n", + "47050 2011-09-16 \n", + "47924 2005-07-20 \n", + "47930 2006-01-01 \n", + "53847 2019-02-14 \n", + "56044 NaN \n", + "62023 1918-06-23 \n", + "68517 1930-08-08 \n", + "69609 NaN \n", + "70879 NaN \n", + "72084 1997-04-04 \n", + "82089 NaN \n", + "83644 2020-07-22 \n", + "90937 NaN \n", + "90978 NaN \n", + "92337 NaN \n", + "103745 NaN \n", + "107864 NaN \n", + "119636 NaN \n", + "128066 NaN \n", + "130375 NaN \n", + "131627 NaN \n", + "134610 NaN " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# bios[bios[\"born_city\"]==\"Mumbai\" and (bios[\"NOC\"]==\"India\")]\n", + "bios[bios[\"born_city\"]==\"Mumbai\"]" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "c9756d65", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " athlete_id name born_date born_city born_region \\\n", + "19002 19135 Eliza Nelson 1956-09-27 Pune (Poona) Maharashtra \n", + "104819 105845 Nikhil Kanetkar 1979-05-13 Pune (Poona) Maharashtra \n", + "118302 119992 Frank Brewin 1909-10-21 Pune (Poona) Maharashtra \n", + "131622 134436 Anirban Lahiri 1987-06-29 Pune (Poona) Maharashtra \n", + "\n", + " born_country NOC height_cm weight_kg died_date \n", + "19002 IND India 160.0 NaN NaN \n", + "104819 IND India 173.0 63.0 NaN \n", + "118302 IND India NaN NaN 1976-04-21 \n", + "131622 IND India 175.0 NaN NaN \n", + "\n" + ] + } + ], + "source": [ + "bios.query('born_region==\"Maharashtra\" and NOC==\"India\"')\n", + "bios.query('born_city==\"Pune (Poona)\" and NOC==\"India\"')\n", + "PuneAth=bios.query('born_city==\"Pune (Poona)\" and NOC==\"India\"')\n", + "\n", + "print(PuneAth)\n", + "print(type(PuneAth))" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.13.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}