{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "Kg4CJ3v0I6hZ", "colab": { "base_uri": "https://localhost:8080/" }, "collapsed": true, "outputId": "18b3537f-afff-436f-84c4-6abd7ee709ee" }, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " App Category Rating \\\n", "0 Photo Editor & Candy Camera & Grid & ScrapBook ART_AND_DESIGN 4.1 \n", "1 Coloring book moana ART_AND_DESIGN 3.9 \n", "2 U Launcher Lite – FREE Live Cool Themes, Hide ... ART_AND_DESIGN 4.7 \n", "3 Sketch - Draw & Paint ART_AND_DESIGN 4.5 \n", "4 Pixel Draw - Number Art Coloring Book ART_AND_DESIGN 4.3 \n", "\n", " Reviews Size Installs Type Price Content Rating \\\n", "0 159 19M 10,000+ Free 0 Everyone \n", "1 967 14M 500,000+ Free 0 Everyone \n", "2 87510 8.7M 5,000,000+ Free 0 Everyone \n", "3 215644 25M 50,000,000+ Free 0 Teen \n", "4 967 2.8M 100,000+ Free 0 Everyone \n", "\n", " Genres Last Updated Current Ver \\\n", "0 Art & Design January 7, 2018 1.0.0 \n", "1 Art & Design;Pretend Play January 15, 2018 2.0.0 \n", "2 Art & Design August 1, 2018 1.2.4 \n", "3 Art & Design June 8, 2018 Varies with device \n", "4 Art & Design;Creativity June 20, 2018 1.1 \n", "\n", " Android Ver \n", "0 4.0.3 and up \n", "1 4.0.3 and up \n", "2 4.0.3 and up \n", "3 4.2 and up \n", "4 4.4 and up " ], "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", "
AppCategoryRatingReviewsSizeInstallsTypePriceContent RatingGenresLast UpdatedCurrent VerAndroid Ver
0Photo Editor & Candy Camera & Grid & ScrapBookART_AND_DESIGN4.115919M10,000+Free0EveryoneArt & DesignJanuary 7, 20181.0.04.0.3 and up
1Coloring book moanaART_AND_DESIGN3.996714M500,000+Free0EveryoneArt & Design;Pretend PlayJanuary 15, 20182.0.04.0.3 and up
2U Launcher Lite – FREE Live Cool Themes, Hide ...ART_AND_DESIGN4.7875108.7M5,000,000+Free0EveryoneArt & DesignAugust 1, 20181.2.44.0.3 and up
3Sketch - Draw & PaintART_AND_DESIGN4.521564425M50,000,000+Free0TeenArt & DesignJune 8, 2018Varies with device4.2 and up
4Pixel Draw - Number Art Coloring BookART_AND_DESIGN4.39672.8M100,000+Free0EveryoneArt & Design;CreativityJune 20, 20181.14.4 and up
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 10841,\n \"fields\": [\n {\n \"column\": \"App\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 9660,\n \"samples\": [\n \"Run R Script - Online Statistical Data Analysis\",\n \"EURES - Your Job in Europe\",\n \"Dog Licks Screen Wallpaper\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Category\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 34,\n \"samples\": [\n \"LIBRARIES_AND_DEMO\",\n \"MEDICAL\",\n \"PRODUCTIVITY\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Rating\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.5374313031477594,\n \"min\": 1.0,\n \"max\": 19.0,\n \"num_unique_values\": 40,\n \"samples\": [\n 5.0,\n 3.4,\n 3.3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Reviews\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 6002,\n \"samples\": [\n \"66661\",\n \"7479\",\n \"8978\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Size\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 462,\n \"samples\": [\n \"746k\",\n \"9.4M\",\n \"35M\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Installs\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 22,\n \"samples\": [\n \"10,000+\",\n \"50+\",\n \"5,000+\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Type\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Free\",\n \"Paid\",\n \"0\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Price\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 93,\n \"samples\": [\n \"$17.99\",\n \"$29.99\",\n \"$37.99\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Content Rating\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 6,\n \"samples\": [\n \"Everyone\",\n \"Teen\",\n \"Unrated\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Genres\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 120,\n \"samples\": [\n \"Casual;Action & Adventure\",\n \"Board\",\n \"Auto & Vehicles\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Last Updated\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1378,\n \"samples\": [\n \"March 15, 2016\",\n \"May 14, 2013\",\n \"October 21, 2015\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Current Ver\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 2832,\n \"samples\": [\n \"7.0.4.17908\",\n \"1.2.5.4-11\",\n \"2.5.7.1\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Android Ver\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 33,\n \"samples\": [\n \"2.2 - 7.1.1\",\n \"7.0 and up\",\n \"3.1 and up\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 1 } ], "source": [ "import pandas as pd\n", "\n", "df = pd.read_csv('googleplaystore.csv')\n", "df.head()\n" ] }, { "cell_type": "code", "source": [ "df.info()\n" ], "metadata": { "id": "Q3q-sJUoJIws", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "b540e026-28ec-409b-f542-b55b196cf9ec" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "RangeIndex: 10841 entries, 0 to 10840\n", "Data columns (total 13 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 App 10841 non-null object \n", " 1 Category 10841 non-null object \n", " 2 Rating 9367 non-null float64\n", " 3 Reviews 10841 non-null object \n", " 4 Size 10841 non-null object \n", " 5 Installs 10841 non-null object \n", " 6 Type 10840 non-null object \n", " 7 Price 10841 non-null object \n", " 8 Content Rating 10840 non-null object \n", " 9 Genres 10841 non-null object \n", " 10 Last Updated 10841 non-null object \n", " 11 Current Ver 10833 non-null object \n", " 12 Android Ver 10838 non-null object \n", "dtypes: float64(1), object(12)\n", "memory usage: 1.1+ MB\n" ] } ] }, { "cell_type": "code", "source": [ "categories = {}\n", "\n", "for name in df['Category'].unique():\n", " ct = 0\n", " for value in df['Category']:\n", " if value == name:\n", " ct += 1\n", " categories[name] = ct\n", "\n", "for key, value in categories.items():\n", " print(f'{key}: {value}')\n" ], "metadata": { "id": "OYZkHSjWJI0F", "colab": { "base_uri": "https://localhost:8080/" }, "collapsed": true, "outputId": "1b9e1dda-ee3d-41cf-de90-ab42ab7e588c" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "ART_AND_DESIGN: 65\n", "AUTO_AND_VEHICLES: 85\n", "BEAUTY: 53\n", "BOOKS_AND_REFERENCE: 231\n", "BUSINESS: 460\n", "COMICS: 60\n", "COMMUNICATION: 387\n", "DATING: 234\n", "EDUCATION: 156\n", "ENTERTAINMENT: 149\n", "EVENTS: 64\n", "FINANCE: 366\n", "FOOD_AND_DRINK: 127\n", "HEALTH_AND_FITNESS: 341\n", "HOUSE_AND_HOME: 88\n", "LIBRARIES_AND_DEMO: 85\n", "LIFESTYLE: 382\n", "GAME: 1144\n", "FAMILY: 1972\n", "MEDICAL: 463\n", "SOCIAL: 295\n", "SHOPPING: 260\n", "PHOTOGRAPHY: 335\n", "SPORTS: 384\n", "TRAVEL_AND_LOCAL: 258\n", "TOOLS: 843\n", "PERSONALIZATION: 392\n", "PRODUCTIVITY: 424\n", "PARENTING: 60\n", "WEATHER: 82\n", "VIDEO_PLAYERS: 175\n", "NEWS_AND_MAGAZINES: 283\n", "MAPS_AND_NAVIGATION: 137\n", "1.9: 1\n" ] } ] }, { "cell_type": "code", "source": [ "df['Category'].value_counts()\n" ], "metadata": { "id": "r7m6ctGjJI-O", "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "collapsed": true, "outputId": "90952d8f-cd34-4e34-b918-018f0a3f249d" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Category\n", "FAMILY 1972\n", "GAME 1144\n", "TOOLS 843\n", "MEDICAL 463\n", "BUSINESS 460\n", "PRODUCTIVITY 424\n", "PERSONALIZATION 392\n", "COMMUNICATION 387\n", "SPORTS 384\n", "LIFESTYLE 382\n", "FINANCE 366\n", "HEALTH_AND_FITNESS 341\n", "PHOTOGRAPHY 335\n", "SOCIAL 295\n", "NEWS_AND_MAGAZINES 283\n", "SHOPPING 260\n", "TRAVEL_AND_LOCAL 258\n", "DATING 234\n", "BOOKS_AND_REFERENCE 231\n", "VIDEO_PLAYERS 175\n", "EDUCATION 156\n", "ENTERTAINMENT 149\n", "MAPS_AND_NAVIGATION 137\n", "FOOD_AND_DRINK 127\n", "HOUSE_AND_HOME 88\n", "AUTO_AND_VEHICLES 85\n", "LIBRARIES_AND_DEMO 85\n", "WEATHER 82\n", "ART_AND_DESIGN 65\n", "EVENTS 64\n", "PARENTING 60\n", "COMICS 60\n", "BEAUTY 53\n", "1.9 1\n", "Name: count, dtype: int64" ], "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", "
count
Category
FAMILY1972
GAME1144
TOOLS843
MEDICAL463
BUSINESS460
PRODUCTIVITY424
PERSONALIZATION392
COMMUNICATION387
SPORTS384
LIFESTYLE382
FINANCE366
HEALTH_AND_FITNESS341
PHOTOGRAPHY335
SOCIAL295
NEWS_AND_MAGAZINES283
SHOPPING260
TRAVEL_AND_LOCAL258
DATING234
BOOKS_AND_REFERENCE231
VIDEO_PLAYERS175
EDUCATION156
ENTERTAINMENT149
MAPS_AND_NAVIGATION137
FOOD_AND_DRINK127
HOUSE_AND_HOME88
AUTO_AND_VEHICLES85
LIBRARIES_AND_DEMO85
WEATHER82
ART_AND_DESIGN65
EVENTS64
PARENTING60
COMICS60
BEAUTY53
1.91
\n", "

" ] }, "metadata": {}, "execution_count": 6 } ] }, { "cell_type": "code", "source": [ "types = {}\n", "\n", "for name in df['Type'].unique():\n", " ct = 0\n", " for value in df['Type']:\n", " if value == name:\n", " ct += 1\n", " types[name] = ct\n", "\n", "print(types)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "DzYsStbMP1ac", "outputId": "92599dbf-9d69-42e9-c6b0-34db67e0bd6d" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "{'Free': 10039, 'Paid': 800, nan: 0, '0': 1}\n" ] } ] }, { "cell_type": "code", "source": [ "(df['Type'].value_counts(normalize=True) * 100).round(2)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 209 }, "id": "hBRUgeI1P1dw", "outputId": "a52b5079-76b5-471b-cd8c-fba5a3c45ef4" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Type\n", "Free 92.61\n", "Paid 7.38\n", "0 0.01\n", "Name: proportion, dtype: float64" ], "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", "
proportion
Type
Free92.61
Paid7.38
00.01
\n", "

" ] }, "metadata": {}, "execution_count": 8 } ] }, { "cell_type": "code", "source": [ "content_rating = {}\n", "\n", "for name in df['Content Rating'].unique():\n", " ct = 0\n", " for value in df['Content Rating']:\n", " if value == name:\n", " ct += 1\n", " content_rating[name] = ct\n", "\n", "print(content_rating)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "tnmmQLYnT3NX", "outputId": "9eb1aaaf-e756-4121-9e8e-e2820cff6aa4" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "{'Everyone': 8714, 'Teen': 1208, 'Everyone 10+': 414, 'Mature 17+': 499, 'Adults only 18+': 3, 'Unrated': 2, nan: 0}\n" ] } ] }, { "cell_type": "code", "source": [ "\n", "df['Content Rating'].value_counts()\n", "\n", "(df['Content Rating'].value_counts(normalize=True) * 100).round(2)\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 303 }, "id": "P51F6pjnT3Px", "outputId": "f0c1173e-b600-4e35-93f6-64078982273a" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Content Rating\n", "Everyone 80.39\n", "Teen 11.14\n", "Mature 17+ 4.60\n", "Everyone 10+ 3.82\n", "Adults only 18+ 0.03\n", "Unrated 0.02\n", "Name: proportion, dtype: float64" ], "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", "
proportion
Content Rating
Everyone80.39
Teen11.14
Mature 17+4.60
Everyone 10+3.82
Adults only 18+0.03
Unrated0.02
\n", "

" ] }, "metadata": {}, "execution_count": 10 } ] }, { "cell_type": "code", "source": [ "df['Reviews'].describe()\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 209 }, "id": "8VGP9LcfT3SY", "outputId": "9bf5942b-f938-4886-f6d5-70c4ef522663" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "count 10841\n", "unique 6002\n", "top 0\n", "freq 596\n", "Name: Reviews, dtype: object" ], "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", "
Reviews
count10841
unique6002
top0
freq596
\n", "

" ] }, "metadata": {}, "execution_count": 11 } ] }, { "cell_type": "code", "source": [ "categorical_cols = ['Category', 'Type', 'Content Rating']\n", "\n", "for col in categorical_cols:\n", " print(f\"\\nAnalysis for {col}\")\n", " print(df[col].value_counts())\n" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "HUzTp02YT3VA", "outputId": "bb2368c3-8c3e-4be1-e0b5-5839a2a084b3" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "Analysis for Category\n", "Category\n", "FAMILY 1972\n", "GAME 1144\n", "TOOLS 843\n", "MEDICAL 463\n", "BUSINESS 460\n", "PRODUCTIVITY 424\n", "PERSONALIZATION 392\n", "COMMUNICATION 387\n", "SPORTS 384\n", "LIFESTYLE 382\n", "FINANCE 366\n", "HEALTH_AND_FITNESS 341\n", "PHOTOGRAPHY 335\n", "SOCIAL 295\n", "NEWS_AND_MAGAZINES 283\n", "SHOPPING 260\n", "TRAVEL_AND_LOCAL 258\n", "DATING 234\n", "BOOKS_AND_REFERENCE 231\n", "VIDEO_PLAYERS 175\n", "EDUCATION 156\n", "ENTERTAINMENT 149\n", "MAPS_AND_NAVIGATION 137\n", "FOOD_AND_DRINK 127\n", "HOUSE_AND_HOME 88\n", "AUTO_AND_VEHICLES 85\n", "LIBRARIES_AND_DEMO 85\n", "WEATHER 82\n", "ART_AND_DESIGN 65\n", "EVENTS 64\n", "PARENTING 60\n", "COMICS 60\n", "BEAUTY 53\n", "1.9 1\n", "Name: count, dtype: int64\n", "\n", "Analysis for Type\n", "Type\n", "Free 10039\n", "Paid 800\n", "0 1\n", "Name: count, dtype: int64\n", "\n", "Analysis for Content Rating\n", "Content Rating\n", "Everyone 8714\n", "Teen 1208\n", "Mature 17+ 499\n", "Everyone 10+ 414\n", "Adults only 18+ 3\n", "Unrated 2\n", "Name: count, dtype: int64\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "xK9W40_VT3X4" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "8BRZrSsrT3ba" }, "execution_count": null, "outputs": [] } ] }