The project intends to guide IOS and Android developer to which free apps where the ROI depends on ads, are more profitable and to help them understand what type of apps are likely to attract more users on Google Play and the App Store.
As of September 2018, there were approximately 2 million iOS apps available on the App Store, and 2.1 million Android apps on Google Play. So we'll try to analyze a sample of the data instead.These are two data sets that seem suitable for our goals:
#Importing reader from csv module
from csv import reader
#Creating a function to open any of the datasets
def open_dataset(file):
opened_file = open(file, encoding='utf8')
read_file = reader(opened_file)
data_set = list(read_file)
return data_set
#Reading the two datasets into list of lists
ios_data = open_dataset('AppleStore.csv')
google_data = open_dataset('googleplaystore.csv')
IOS Data
#Creating a function that can print rows in a readable way
def explore_data(dataset, start, end, rows_and_columns=False):
dataset_slice = dataset[start:end]
for row in dataset_slice:
print(row)
print('\n')
if rows_and_columns:
print('Number of rows:', len(dataset))
print('Number of columns:', len(dataset[0]))
#Exploring IOS dataset
explore_data(ios_data, 0, 5, True)
['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic'] ['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1'] ['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1'] ['529479190', 'Clash of Clans', '116476928', 'USD', '0.0', '2130805', '579', '4.5', '4.5', '9.24.12', '9+', 'Games', '38', '5', '18', '1'] ['420009108', 'Temple Run', '65921024', 'USD', '0.0', '1724546', '3842', '4.5', '4.0', '1.6.2', '9+', 'Games', '40', '5', '1', '1'] Number of rows: 7198 Number of columns: 16
#Printing only column names
explore_data(ios_data, 0, 1)
['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic']
Comments:
Google Play Data
#Exploring Google Play dataset
explore_data(google_data, 0, 5, True)
['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver'] ['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up'] ['Coloring book moana', 'ART_AND_DESIGN', '3.9', '967', '14M', '500,000+', 'Free', '0', 'Everyone', 'Art & Design;Pretend Play', 'January 15, 2018', '2.0.0', '4.0.3 and up'] ['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up'] ['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up'] Number of rows: 10842 Number of columns: 13
#Printing only column names
explore_data(google_data, 0, 1)
['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver']
Comments:
In the previous step, we opened the two data sets and performed a brief exploration of the data. Before beginning our analysis, we need to make sure the data we analyze is accurate, This means that we need to:
We are only interested in apps that are free to download and install, and that are directed toward an English-speaking audience. This means that we'll need to:
#Checking if there is any other row which has the same issue of missing values
google_cols = google_data[0]
for row in google_data[1:]:
if len(row) != len(google_cols):
print(google_data.index(row))
10473
#Exploring entry 10472 at index 10473 (header row included)
print(google_data[10473])
print("\n")
print(len(google_data[0]), len(google_data[10473]))
['Life Made WI-Fi Touchscreen Photo Frame', '1.9', '19', '3.0M', '1,000+', 'Free', '0', 'Everyone', '', 'February 11, 2018', '1.0.19', '4.0 and up'] 13 12
#Removing the row with the missing data
del google_data[10473]
#Checking if the row was deleted correctly
print(google_data[10473])
['osmino Wi-Fi: free WiFi', 'TOOLS', '4.2', '134203', '4.1M', '10,000,000+', 'Free', '0', 'Everyone', 'Tools', 'August 7, 2018', '6.06.14', '4.4 and up']
for row in google_data:
if row[0] == 'Instagram':
print(row)
['Instagram', 'SOCIAL', '4.5', '66577313', 'Varies with device', '1,000,000,000+', 'Free', '0', 'Teen', 'Social', 'July 31, 2018', 'Varies with device', 'Varies with device'] ['Instagram', 'SOCIAL', '4.5', '66577446', 'Varies with device', '1,000,000,000+', 'Free', '0', 'Teen', 'Social', 'July 31, 2018', 'Varies with device', 'Varies with device'] ['Instagram', 'SOCIAL', '4.5', '66577313', 'Varies with device', '1,000,000,000+', 'Free', '0', 'Teen', 'Social', 'July 31, 2018', 'Varies with device', 'Varies with device'] ['Instagram', 'SOCIAL', '4.5', '66509917', 'Varies with device', '1,000,000,000+', 'Free', '0', 'Teen', 'Social', 'July 31, 2018', 'Varies with device', 'Varies with device']
#Checking the duplicate data if any
uniq_data = []
dupl_data = []
for row in google_data[1:]:
if row[0] in uniq_data:
dupl_data.append(row[0])
else:
uniq_data.append(row[0])
print(dupl_data[:5])
print('\n')
#Checking the number of duplicate entries
print(len(dupl_data))
['Quick PDF Scanner + OCR FREE', 'Box', 'Google My Business', 'ZOOM Cloud Meetings', 'join.me - Simple Meetings'] 1181
#Creating a cleaning dictionary with app name as key and number of reviews as value
cleaning_dic = {}
for row in google_data[1:]:
app_name = row[0]
n_rev = float(row[3]) #Number of reviews
if app_name in cleaning_dic and n_rev > cleaning_dic[app_name]:
cleaning_dic[app_name] = n_rev
elif app_name not in cleaning_dic:
cleaning_dic[app_name] = n_rev
print(len(cleaning_dic))
9659
#Mapping the app name to the cleaning dictionary and add the row to google_cleaned list if it wasn`t already added as checked by added_already list
google_cleaned = []
google_cleaned.append(google_data[0])
added_already = []
for row in google_data[1:]:
if float(row[3]) == cleaning_dic[row[0]] and row[0] not in added_already:
google_cleaned.append(row)
added_already.append(row[0])
print(len(google_cleaned))
9660
ios_uniq = []
ios_dupl = []
for row in ios_data[1:]:
if row[0] in ios_uniq:
ios_dupl.append(row[0])
else:
ios_uniq.append(row[0])
print(ios_dupl[:5])
print('\n')
print(len(ios_dupl))
[] 0
There is no duplicates in IOS data as shown above
#Creating a function that checks the character in a string if its ord() is below 127 (English) and if the string has more than 3 non-english characters it will be marked as non_english app.
def is_com_eng(a_string):
char_list = []
for char in a_string:
if ord(char) > 127:
char_list.append(char)
if len(char_list) > 3:
return False
return True
#Testing the function
print(is_com_eng('Instagram'))
print(is_com_eng('爱奇艺PPS -《欢乐颂2》电视剧热播'))
print(is_com_eng('Docs To Go™ Free Office Suite'))
print(is_com_eng('Instachat 😜'))
True False True True
#Using the is_com_eng function to filter the english apps on both google and ios apps
#IOS apps filteration
ios_data_eng = []
for row in ios_data:
if is_com_eng(row[1]):
ios_data_eng.append(row)
#Google data filteration
google_data_eng = []
for row in google_cleaned:
if is_com_eng(row[0]):
google_data_eng.append(row)
#Exploring the 2 datasets
print(ios_data_eng[:5], '\n', len(ios_data_eng), '\n')
print(google_data_eng[:5], '\n', len(google_data_eng))
[['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic'], ['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1'], ['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1'], ['529479190', 'Clash of Clans', '116476928', 'USD', '0.0', '2130805', '579', '4.5', '4.5', '9.24.12', '9+', 'Games', '38', '5', '18', '1'], ['420009108', 'Temple Run', '65921024', 'USD', '0.0', '1724546', '3842', '4.5', '4.0', '1.6.2', '9+', 'Games', '40', '5', '1', '1']] 6184 [['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver'], ['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up'], ['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up'], ['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up'], ['Pixel Draw - Number Art Coloring Book', 'ART_AND_DESIGN', '4.3', '967', '2.8M', '100,000+', 'Free', '0', 'Everyone', 'Art & Design;Creativity', 'June 20, 2018', '1.1', '4.4 and up']] 9615
#Selecting the free apps from IOS data
ios_final = []
ios_final.append(ios_data_eng[0])
for row in ios_data_eng:
if row[4] == '0.0':
ios_final.append(row)
print("Number of IOS free apps: ", len(ios_final))
print(ios_final[:3])
print('\n')
#Selecting the free apps from Google data
google_final = []
google_final.append(google_data_eng[0])
for row in google_data_eng:
if row[7] == '0':
google_final.append(row)
print("Number of Google free apps: ", len(google_final))
print(google_final[:3])
Number of IOS free apps: 3223 [['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic'], ['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1'], ['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1']] Number of Google free apps: 8865 [['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver'], ['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up'], ['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up']]
As we mentioned in the introduction, our aim is to determine the kinds of apps that are likely to attract more users because our revenue is highly influenced by the number of people using our apps.
To minimize risks and overhead, our validation strategy for an app idea is comprised of three steps:
Because our end goal is to add the app on both Google Play and the App Store, we need to find app profiles that are successful on both markets. For instance, a profile that works well for both markets might be a productivity app that makes use of gamification.
We will start the analysis by getting a sense of what are the most common genres for each market. For this, we'll need to build frequency tables for a few columns in our data sets.
From IOS data description we can find that the prime_genre
column contains the information we need and in Google data it`s both Genre
and Category
columns.
We'll build two functions we can use to analyze the frequency tables:
#Creating a function to generate frequency tables with percentages
def freq_table(dataset, index):
table = {}
total_val = 0
for row in dataset[1:]:
total_val += 1
if row[index] in table:
table[row[index]] += 1
else:
table[row[index]] = 1
for k in table:
table[k] = (table[k] / total_val) * 100
return table
#Creating a function that convert the freq table into list of tuples and sort it in a descending order and print the order
def display_table(dataset, index):
table = freq_table(dataset, index)
table_display = []
for key in table:
key_val_as_tuple = (table[key], key)
table_display.append(key_val_as_tuple)
table_sorted = sorted(table_display, reverse = True)
for entry in table_sorted:
print(entry[1], ':', entry[0])
#Exploring prime_genre column in IOS data
print("IOS prim_genre FREQUENCIES:")
display_table(ios_final, 11)
print('\n')
#Exploring Genre column in Google data
print("GOOGLE Genre FREQUENCIES:")
display_table(google_final, 9)
print('\n')
#Exploring Category column in Google data
print("GOOGLE Category FREQUENCIES:")
display_table(google_final, 1)
IOS prim_genre FREQUENCIES: Games : 58.16263190564867 Entertainment : 7.883302296710118 Photo & Video : 4.9658597144630665 Education : 3.662321539416512 Social Networking : 3.2898820608317814 Shopping : 2.60707635009311 Utilities : 2.5139664804469275 Sports : 2.1415270018621975 Music : 2.0484171322160147 Health & Fitness : 2.0173805090006205 Productivity : 1.7380509000620732 Lifestyle : 1.5828677839851024 News : 1.3345747982619491 Travel : 1.2414649286157666 Finance : 1.1173184357541899 Weather : 0.8690254500310366 Food & Drink : 0.8069522036002483 Reference : 0.5586592178770949 Business : 0.5276225946617008 Book : 0.4345127250155183 Navigation : 0.186219739292365 Medical : 0.186219739292365 Catalogs : 0.12414649286157665 GOOGLE Genre FREQUENCIES: Tools : 8.449909747292418 Entertainment : 6.069494584837545 Education : 5.347472924187725 Business : 4.591606498194946 Productivity : 3.892148014440433 Lifestyle : 3.892148014440433 Finance : 3.7003610108303246 Medical : 3.531137184115524 Sports : 3.463447653429603 Personalization : 3.3167870036101084 Communication : 3.2378158844765346 Action : 3.1024368231046933 Health & Fitness : 3.0798736462093865 Photography : 2.944494584837545 News & Magazines : 2.7978339350180503 Social : 2.6624548736462095 Travel & Local : 2.3240072202166067 Shopping : 2.2450361010830324 Books & Reference : 2.1435018050541514 Simulation : 2.0419675090252705 Dating : 1.861462093862816 Arcade : 1.8501805054151623 Video Players & Editors : 1.7712093862815883 Casual : 1.7599277978339352 Maps & Navigation : 1.3989169675090252 Food & Drink : 1.2409747292418771 Puzzle : 1.128158844765343 Racing : 0.9927797833935018 Role Playing : 0.9363718411552346 Libraries & Demo : 0.9363718411552346 Auto & Vehicles : 0.9250902527075812 Strategy : 0.9138086642599278 House & Home : 0.8235559566787004 Weather : 0.8009927797833934 Events : 0.7107400722021661 Adventure : 0.6768953068592057 Comics : 0.6092057761732852 Beauty : 0.5979241877256317 Art & Design : 0.5979241877256317 Parenting : 0.4963898916967509 Card : 0.45126353790613716 Casino : 0.42870036101083037 Trivia : 0.41741877256317694 Educational;Education : 0.39485559566787 Board : 0.3835740072202166 Educational : 0.3722924187725632 Education;Education : 0.33844765342960287 Word : 0.2594765342960289 Casual;Pretend Play : 0.236913357400722 Music : 0.2030685920577617 Racing;Action & Adventure : 0.16922382671480143 Puzzle;Brain Games : 0.16922382671480143 Entertainment;Music & Video : 0.16922382671480143 Casual;Brain Games : 0.13537906137184114 Casual;Action & Adventure : 0.13537906137184114 Arcade;Action & Adventure : 0.12409747292418773 Action;Action & Adventure : 0.10153429602888085 Educational;Pretend Play : 0.09025270758122744 Simulation;Action & Adventure : 0.078971119133574 Parenting;Education : 0.078971119133574 Entertainment;Brain Games : 0.078971119133574 Board;Brain Games : 0.078971119133574 Parenting;Music & Video : 0.06768953068592057 Educational;Brain Games : 0.06768953068592057 Casual;Creativity : 0.06768953068592057 Art & Design;Creativity : 0.06768953068592057 Education;Pretend Play : 0.056407942238267145 Role Playing;Pretend Play : 0.04512635379061372 Education;Creativity : 0.04512635379061372 Role Playing;Action & Adventure : 0.033844765342960284 Puzzle;Action & Adventure : 0.033844765342960284 Entertainment;Creativity : 0.033844765342960284 Entertainment;Action & Adventure : 0.033844765342960284 Educational;Creativity : 0.033844765342960284 Educational;Action & Adventure : 0.033844765342960284 Education;Music & Video : 0.033844765342960284 Education;Brain Games : 0.033844765342960284 Education;Action & Adventure : 0.033844765342960284 Adventure;Action & Adventure : 0.033844765342960284 Video Players & Editors;Music & Video : 0.02256317689530686 Sports;Action & Adventure : 0.02256317689530686 Simulation;Pretend Play : 0.02256317689530686 Puzzle;Creativity : 0.02256317689530686 Music;Music & Video : 0.02256317689530686 Entertainment;Pretend Play : 0.02256317689530686 Casual;Education : 0.02256317689530686 Board;Action & Adventure : 0.02256317689530686 Video Players & Editors;Creativity : 0.01128158844765343 Trivia;Education : 0.01128158844765343 Travel & Local;Action & Adventure : 0.01128158844765343 Tools;Education : 0.01128158844765343 Strategy;Education : 0.01128158844765343 Strategy;Creativity : 0.01128158844765343 Strategy;Action & Adventure : 0.01128158844765343 Simulation;Education : 0.01128158844765343 Role Playing;Brain Games : 0.01128158844765343 Racing;Pretend Play : 0.01128158844765343 Puzzle;Education : 0.01128158844765343 Parenting;Brain Games : 0.01128158844765343 Music & Audio;Music & Video : 0.01128158844765343 Lifestyle;Pretend Play : 0.01128158844765343 Lifestyle;Education : 0.01128158844765343 Health & Fitness;Education : 0.01128158844765343 Health & Fitness;Action & Adventure : 0.01128158844765343 Entertainment;Education : 0.01128158844765343 Communication;Creativity : 0.01128158844765343 Comics;Creativity : 0.01128158844765343 Casual;Music & Video : 0.01128158844765343 Card;Action & Adventure : 0.01128158844765343 Books & Reference;Education : 0.01128158844765343 Art & Design;Pretend Play : 0.01128158844765343 Art & Design;Action & Adventure : 0.01128158844765343 Arcade;Pretend Play : 0.01128158844765343 Adventure;Education : 0.01128158844765343 GOOGLE Category FREQUENCIES: FAMILY : 18.907942238267147 GAME : 9.724729241877256 TOOLS : 8.461191335740072 BUSINESS : 4.591606498194946 LIFESTYLE : 3.9034296028880866 PRODUCTIVITY : 3.892148014440433 FINANCE : 3.7003610108303246 MEDICAL : 3.531137184115524 SPORTS : 3.395758122743682 PERSONALIZATION : 3.3167870036101084 COMMUNICATION : 3.2378158844765346 HEALTH_AND_FITNESS : 3.0798736462093865 PHOTOGRAPHY : 2.944494584837545 NEWS_AND_MAGAZINES : 2.7978339350180503 SOCIAL : 2.6624548736462095 TRAVEL_AND_LOCAL : 2.33528880866426 SHOPPING : 2.2450361010830324 BOOKS_AND_REFERENCE : 2.1435018050541514 DATING : 1.861462093862816 VIDEO_PLAYERS : 1.7937725631768955 MAPS_AND_NAVIGATION : 1.3989169675090252 FOOD_AND_DRINK : 1.2409747292418771 EDUCATION : 1.1620036101083033 ENTERTAINMENT : 0.9589350180505415 LIBRARIES_AND_DEMO : 0.9363718411552346 AUTO_AND_VEHICLES : 0.9250902527075812 HOUSE_AND_HOME : 0.8235559566787004 WEATHER : 0.8009927797833934 EVENTS : 0.7107400722021661 PARENTING : 0.6543321299638989 ART_AND_DESIGN : 0.6430505415162455 COMICS : 0.6204873646209386 BEAUTY : 0.5979241877256317
For the english free apps on both stores and from the findings above we can notice
Now, we'd like to get an idea about the kind of apps with the most users. One way to find out what genres are the most popular (have the most users) is to calculate the average number of installs for each app genre. For the Google Play data set, we can find this information in the Installs
column, but this information is missing for the App Store data set. As a workaround, we'll take the total number of user ratings as a proxy, which we can find in the rating_count_tot
app.
Let's start with calculating the average number of user ratings per app genre on the App Store. To do that, we'll need to:
ios_gen_table = freq_table(ios_final, 11) #Creating a frequency table for the prime_genre column in IOS data
genre_rat_num = []
for genre in ios_gen_table:
total = 0 #Storing the sum of user ratings specific for each genre
len_genre = 0 #Storing the number of apps specific to each genre
for row in ios_final:
genre_app = row[11]
if genre == genre_app:
total += float(row[5])
len_genre +=1
avg_rat_gen = total / len_genre
genre_rat_num.append((avg_rat_gen, genre))
sorted_genre_rat_num = sorted(genre_rat_num, reverse=True)
for v in sorted_genre_rat_num:
print(v[1], ': ', v[0])
Navigation : 86090.33333333333 Reference : 74942.11111111111 Social Networking : 71548.34905660378 Music : 57326.530303030304 Weather : 52279.892857142855 Book : 39758.5 Food & Drink : 33333.92307692308 Finance : 31467.944444444445 Photo & Video : 28441.54375 Travel : 28243.8 Shopping : 26919.690476190477 Health & Fitness : 23298.015384615384 Sports : 23008.898550724636 Games : 22788.6696905016 News : 21248.023255813954 Productivity : 21028.410714285714 Utilities : 18684.456790123455 Lifestyle : 16485.764705882353 Entertainment : 14029.830708661417 Business : 7491.117647058823 Education : 7003.983050847458 Catalogs : 4004.0 Medical : 612.0
for row in ios_final:
if row[11] == 'Navigation':
print(row[1] , ': ', row[5])
Waze - GPS Navigation, Maps & Real-time Traffic : 345046 Google Maps - Navigation & Transit : 154911 Geocaching® : 12811 CoPilot GPS – Car Navigation & Offline Maps : 3582 ImmobilienScout24: Real Estate Search in Germany : 187 Railway Route Search : 5
for row in ios_final:
if row[11] == 'Reference':
print(row[1] , ': ', row[5])
Bible : 985920 Dictionary.com Dictionary & Thesaurus : 200047 Dictionary.com Dictionary & Thesaurus for iPad : 54175 Google Translate : 26786 Muslim Pro: Ramadan 2017 Prayer Times, Azan, Quran : 18418 New Furniture Mods - Pocket Wiki & Game Tools for Minecraft PC Edition : 17588 Merriam-Webster Dictionary : 16849 Night Sky : 12122 City Maps for Minecraft PE - The Best Maps for Minecraft Pocket Edition (MCPE) : 8535 LUCKY BLOCK MOD ™ for Minecraft PC Edition - The Best Pocket Wiki & Mods Installer Tools : 4693 GUNS MODS for Minecraft PC Edition - Mods Tools : 1497 Guides for Pokémon GO - Pokemon GO News and Cheats : 826 WWDC : 762 Horror Maps for Minecraft PE - Download The Scariest Maps for Minecraft Pocket Edition (MCPE) Free : 718 VPN Express : 14 Real Bike Traffic Rider Virtual Reality Glasses : 8 教えて!goo : 0 Jishokun-Japanese English Dictionary & Translator : 0
for row in ios_final:
if row[11] == 'Social Networking':
print(row[1] , ': ', row[5])
Facebook : 2974676 Pinterest : 1061624 Skype for iPhone : 373519 Messenger : 351466 Tumblr : 334293 WhatsApp Messenger : 287589 Kik : 260965 ooVoo – Free Video Call, Text and Voice : 177501 TextNow - Unlimited Text + Calls : 164963 Viber Messenger – Text & Call : 164249 Followers - Social Analytics For Instagram : 112778 MeetMe - Chat and Meet New People : 97072 We Heart It - Fashion, wallpapers, quotes, tattoos : 90414 InsTrack for Instagram - Analytics Plus More : 85535 Tango - Free Video Call, Voice and Chat : 75412 LinkedIn : 71856 Match™ - #1 Dating App. : 60659 Skype for iPad : 60163 POF - Best Dating App for Conversations : 52642 Timehop : 49510 Find My Family, Friends & iPhone - Life360 Locator : 43877 Whisper - Share, Express, Meet : 39819 Hangouts : 36404 LINE PLAY - Your Avatar World : 34677 WeChat : 34584 Badoo - Meet New People, Chat, Socialize. : 34428 Followers + for Instagram - Follower Analytics : 28633 GroupMe : 28260 Marco Polo Video Walkie Talkie : 27662 Miitomo : 23965 SimSimi : 23530 Grindr - Gay and same sex guys chat, meet and date : 23201 Wishbone - Compare Anything : 20649 imo video calls and chat : 18841 After School - Funny Anonymous School News : 18482 Quick Reposter - Repost, Regram and Reshare Photos : 17694 Weibo HD : 16772 Repost for Instagram : 15185 Live.me – Live Video Chat & Make Friends Nearby : 14724 Nextdoor : 14402 Followers Analytics for Instagram - InstaReport : 13914 YouNow: Live Stream Video Chat : 12079 FollowMeter for Instagram - Followers Tracking : 11976 LINE : 11437 eHarmony™ Dating App - Meet Singles : 11124 Discord - Chat for Gamers : 9152 QQ : 9109 Telegram Messenger : 7573 Weibo : 7265 Periscope - Live Video Streaming Around the World : 6062 Chat for Whatsapp - iPad Version : 5060 QQ HD : 5058 Followers Analysis Tool For Instagram App Free : 4253 live.ly - live video streaming : 4145 Houseparty - Group Video Chat : 3991 SOMA Messenger : 3232 Monkey : 3060 Down To Lunch : 2535 Flinch - Video Chat Staring Contest : 2134 Highrise - Your Avatar Community : 2011 LOVOO - Dating Chat : 1985 PlayStation®Messages : 1918 BOO! - Video chat camera with filters & stickers : 1805 Qzone : 1649 Chatous - Chat with new people : 1609 Kiwi - Q&A : 1538 GhostCodes - a discovery app for Snapchat : 1313 Jodel : 1193 FireChat : 1037 Google Duo - simple video calling : 1033 Fiesta by Tango - Chat & Meet New People : 885 Google Allo — smart messaging : 862 Peach — share vividly : 727 Hey! VINA - Where Women Meet New Friends : 719 Battlefield™ Companion : 689 All Devices for WhatsApp - Messenger for iPad : 682 Chat for Pokemon Go - GoChat : 500 IAmNaughty – Dating App to Meet New People Online : 463 Qzone HD : 458 Zenly - Locate your friends in realtime : 427 League of Legends Friends : 420 豆瓣 : 407 Candid - Speak Your Mind Freely : 398 知乎 : 397 Selfeo : 366 Fake-A-Location Free ™ : 354 Popcorn Buzz - Free Group Calls : 281 Fam — Group video calling for iMessage : 279 QQ International : 274 Ameba : 269 SoundCloud Pulse: for creators : 240 Tantan : 235 Cougar Dating & Life Style App for Mature Women : 213 Rawr Messenger - Dab your chat : 180 WhenToPost: Best Time to Post Photos for Instagram : 158 Inke—Broadcast an amazing life : 147 Mustknow - anonymous video Q&A : 53 CTFxCmoji : 39 Lobi : 36 Chain: Collaborate On MyVideo Story/Group Video : 35 botman - Real time video chat : 7 BestieBox : 0 MATCH ON LINE chat : 0 niconico ch : 0 LINE BLOG : 0 bit-tube - Live Stream Video Chat : 0
for row in ios_final:
if row[11] == 'Music':
print(row[1] , ': ', row[5])
Pandora - Music & Radio : 1126879 Spotify Music : 878563 Shazam - Discover music, artists, videos & lyrics : 402925 iHeartRadio – Free Music & Radio Stations : 293228 SoundCloud - Music & Audio : 135744 Magic Piano by Smule : 131695 Smule Sing! : 119316 TuneIn Radio - MLB NBA Audiobooks Podcasts Music : 110420 Amazon Music : 106235 SoundHound Song Search & Music Player : 82602 Sonos Controller : 48905 Bandsintown Concerts : 30845 Karaoke - Sing Karaoke, Unlimited Songs! : 28606 My Mixtapez Music : 26286 Sing Karaoke Songs Unlimited with StarMaker : 26227 Ringtones for iPhone & Ringtone Maker : 25403 Musi - Unlimited Music For YouTube : 25193 AutoRap by Smule : 18202 Spinrilla - Mixtapes For Free : 15053 Napster - Top Music & Radio : 14268 edjing Mix:DJ turntable to remix and scratch music : 13580 Free Music - MP3 Streamer & Playlist Manager Pro : 13443 Free Piano app by Yokee : 13016 Google Play Music : 10118 Certified Mixtapes - Hip Hop Albums & Mixtapes : 9975 TIDAL : 7398 YouTube Music : 7109 Nicki Minaj: The Empire : 5196 Sounds app - Music And Friends : 5126 SongFlip - Free Music Streamer : 5004 Simple Radio - Live AM & FM Radio Stations : 4787 Deezer - Listen to your Favorite Music & Playlists : 4677 Ringtones for iPhone with Ringtone Maker : 4013 Bose SoundTouch : 3687 Amazon Alexa : 3018 DatPiff : 2815 Trebel Music - Unlimited Music Downloader : 2570 Free Music Play - Mp3 Streamer & Player : 2496 Acapella from PicPlayPost : 2487 Coach Guitar - Lessons & Easy Tabs For Beginners : 2416 Musicloud - MP3 and FLAC Music Player for Cloud Platforms. : 2211 Piano - Play Keyboard Music Games with Magic Tiles : 1636 Boom: Best Equalizer & Magical Surround Sound : 1375 Music Freedom - Unlimited Free MP3 Music Streaming : 1246 AmpMe - A Portable Social Party Music Speaker : 1047 Medly - Music Maker : 933 Bose Connect : 915 Music Memos : 909 UE BOOM : 612 LiveMixtapes : 555 NOISE : 355 MP3 Music Player & Streamer for Clouds : 329 Musical Video Maker - Create Music clips lip sync : 320 Cloud Music Player - Downloader & Playlist Manager : 319 Remixlive - Remix loops with pads : 288 QQ音乐HD : 224 Blocs Wave - Make & Record Music : 158 PlayGround • Music At Your Fingertips : 150 Music and Chill : 135 The Singing Machine Mobile Karaoke App : 130 radio.de - Der Radioplayer : 64 Free Music - Player & Streamer for Dropbox, OneDrive & Google Drive : 46 NRJ Radio : 38 Smart Music: Streaming Videos and Radio : 17 BOSS Tuner : 13 PetitLyrics : 0
for row in ios_final:
if row[11] == 'Weather':
print(row[1] , ': ', row[5])
The Weather Channel: Forecast, Radar & Alerts : 495626 The Weather Channel App for iPad – best local forecast, radar map, and storm tracking : 208648 WeatherBug - Local Weather, Radar, Maps, Alerts : 188583 MyRadar NOAA Weather Radar Forecast : 150158 AccuWeather - Weather for Life : 144214 Yahoo Weather : 112603 Weather Underground: Custom Forecast & Local Radar : 49192 NOAA Weather Radar - Weather Forecast & HD Radar : 45696 Weather Live Free - Weather Forecast & Alerts : 35702 Storm Radar : 22792 QuakeFeed Earthquake Map, Alerts, and News : 6081 Moji Weather - Free Weather Forecast : 2333 Hurricane by American Red Cross : 1158 Forecast Bar : 375 Hurricane Tracker WESH 2 Orlando, Central Florida : 203 FEMA : 128 iWeather - World weather forecast : 80 Weather - Radar - Storm with Morecast App : 78 Yurekuru Call : 53 Weather & Radar : 37 WRAL Weather Alert : 25 Météo-France : 24 JaxReady : 22 Freddy the Frogcaster's Weather Station : 14 Almanac Long-Range Weather Forecast : 12 TodayAir : 0 wetter.com : 0 WarnWetter : 0
for row in ios_final:
if row[11] == 'Book':
print(row[1] , ': ', row[5])
Kindle – Read eBooks, Magazines & Textbooks : 252076 Audible – audio books, original series & podcasts : 105274 Color Therapy Adult Coloring Book for Adults : 84062 OverDrive – Library eBooks and Audiobooks : 65450 HOOKED - Chat Stories : 47829 BookShout: Read eBooks & Track Your Reading Goals : 879 Dr. Seuss Treasury — 50 best kids books : 451 Green Riding Hood : 392 Weirdwood Manor : 197 MangaZERO - comic reader : 9 ikouhoushi : 0 MangaTiara - love comic reader : 0 謎解き : 0 謎解き2016 : 0
for row in ios_final:
if row[11] == 'Food & Drink':
print(row[1] , ': ', row[5])
Starbucks : 303856 Domino's Pizza USA : 258624 OpenTable - Restaurant Reservations : 113936 Allrecipes Dinner Spinner : 109349 DoorDash - Food Delivery : 25947 UberEATS: Uber for Food Delivery : 17865 Postmates - Food Delivery, Faster : 9519 Dunkin' Donuts - Get Offers, Coupons & Rewards : 9068 Chick-fil-A : 5665 McDonald's : 4050 Deliveroo: Restaurant Delivery - Order Food Nearby : 1702 SONIC Drive-In : 1645 Nowait Guest : 1625 7-Eleven, Inc. : 1356 Outback : 805 Bon Appetit : 750 Starbucks Keyboard : 457 Whataburger : 197 Delish Eatmoji Keyboard : 154 Lieferheld - Delicious food delivery service : 29 Lieferando.de : 29 McDo France : 22 Chefkoch - Rezepte, Kochen, Backen & Kochbuch : 20 Youmiam : 9 Marmiton Twist : 2 Open Food Facts : 1
for row in ios_final:
if row[11] == 'Finance':
print(row[1] , ': ', row[5])
Chase Mobile℠ : 233270 Mint: Personal Finance, Budget, Bills & Money : 232940 Bank of America - Mobile Banking : 119773 PayPal - Send and request money safely : 119487 Credit Karma: Free Credit Scores, Reports & Alerts : 101679 Capital One Mobile : 56110 Citi Mobile® : 48822 Wells Fargo Mobile : 43064 Chase Mobile : 34322 Square Cash - Send Money for Free : 23775 Capital One for iPad : 21858 Venmo : 21090 USAA Mobile : 19946 TaxCaster – Free tax refund calculator : 17516 Amex Mobile : 11421 TurboTax Tax Return App - File 2016 income taxes : 9635 Bank of America - Mobile Banking for iPad : 7569 Wells Fargo for iPad : 2207 Stash Invest: Investing & Financial Education : 1655 Digit: Save Money Without Thinking About It : 1506 IRS2Go : 1329 Capital One CreditWise - Credit score and report : 1019 U by BB&T : 790 Paribus - Rebates When Prices Drop : 768 KeyBank Mobile : 623 VyStar Mobile Banking for iPhone : 434 Sparkasse - Your mobile branch : 77 VyStar Mobile Banking for iPad : 57 Zaim : 44 Ma Banque : 17 Lloyds Bank Mobile Banking : 17 Suica : 10 Halifax Mobile Banking : 8 La Banque Postale : 8 币优铺 : 0 Impots.gouv : 0
From the findings above we can narrow down our selections to the Book and Finance genres, as they have a decent number of users and no specific apps are dominating the market, in another wording the market share looks balanced and promising.
We have data about the number of installs for the Google Play market, so we should be able to get a clearer picture about genre popularity. However, the install numbers don't seem precise enough — we can see that most values are open-ended (100+, 1,000+, 5,000+, etc.). For instance, we don't know whether an app with 100,000+ installs has 100,000 installs, 200,000, or 350,000. However, we don't need very precise data for our purposes — we only want to find out which app genres attract the most users, and we don't need perfect precision with respect to the number of users. We're going to leave the numbers as they are, which means that we'll consider that an app with 100,000+ installs has 100,000 installs, and an app with 1,000,000+ installs has 1,000,000 installs, and so on.
Now let's calculate the average number of installs per app genre for the Google Play data set.
google_gen_table = freq_table(google_final, 1) #Creating freq table for the Category column in Google Play data
google_cat_num =[]
for cat in google_gen_table:
total = 0
len_category = 0
for row in google_final:
category_app = row[1]
if cat == category_app:
n_installs = float(row[5].replace('+','').replace(',', ''))
total += n_installs
len_category += 1
google_avg_num = total / len_category
google_cat_num.append((google_avg_num, cat))
sorted_google_avg_num = sorted(google_cat_num, reverse=True)
for x in sorted_google_avg_num:
print(x[1], ': ', x[0])
COMMUNICATION : 38456119.167247385 VIDEO_PLAYERS : 24727872.452830188 SOCIAL : 23253652.127118643 PHOTOGRAPHY : 17840110.40229885 PRODUCTIVITY : 16787331.344927534 GAME : 15588015.603248259 TRAVEL_AND_LOCAL : 13984077.710144928 ENTERTAINMENT : 11640705.88235294 TOOLS : 10801391.298666667 NEWS_AND_MAGAZINES : 9549178.467741935 BOOKS_AND_REFERENCE : 8767811.894736841 SHOPPING : 7036877.311557789 PERSONALIZATION : 5201482.6122448975 WEATHER : 5074486.197183099 HEALTH_AND_FITNESS : 4188821.9853479853 MAPS_AND_NAVIGATION : 4056941.7741935486 FAMILY : 3695641.8198090694 SPORTS : 3638640.1428571427 ART_AND_DESIGN : 1986335.0877192982 FOOD_AND_DRINK : 1924897.7363636363 EDUCATION : 1833495.145631068 BUSINESS : 1712290.1474201474 LIFESTYLE : 1437816.2687861272 FINANCE : 1387692.475609756 HOUSE_AND_HOME : 1331540.5616438356 DATING : 854028.8303030303 COMICS : 817657.2727272727 AUTO_AND_VEHICLES : 647317.8170731707 LIBRARIES_AND_DEMO : 638503.734939759 PARENTING : 542603.6206896552 BEAUTY : 513151.88679245283 EVENTS : 253542.22222222222 MEDICAL : 120550.61980830671