COPY Matching App Type & Number of Users¶

slicer(ios_data, 0, 3)
row_column_counter(ios_data)

slicer(android_data, 0, 3)
row_column_counter(android_data)

# Row 10472 google data (header exclusive)

print(len(android_data[10473]))
print(android_data[10473])

print(len(android_data[10474]))
print(android_data[10474])

# Curious to see if there are any other rows missing entries.
short_rows = []
for row in android_data:
    if len(row) != 13:
        short_rows.append(row)

print(len(short_rows))

data_copy = []
print('The android data set length is ' + str(len(android_data)))
print('The android data set copy length is ' + str(len(data_copy)))

def refiner(data_set):
    for row in data_set:
        if len(row) == len(data_set[0]):
            data_copy.append(row)
    return 'Data set copied'

refiner(android_data)
print('The android data set length is ' + str(len(android_data)))
print('The android data set copy length is ' + str(len(data_copy)))

android_data = data_copy
print(len(android_data))

for row in android_data:
    app_name = row[0]
    if app_name == 'Slack':
        print(row)

duplicate_apps = []
unique_apps = []

for row in android_data[1:]:
    name = row[0]
    if name in unique_apps:
        duplicate_apps.append(name)
    else:
        unique_apps.append(name)
        
print('Number of unique apps:', len(unique_apps))
print('Number of duplicate apps', len(duplicate_apps))
print('\n')
print('Examples of duplicate apps:', duplicate_apps[:10])
print('\n')

slack_count = 0

for app_name in unique_apps:
    if app_name == 'Slack':
        slack_count += 1
for app_name in duplicate_apps:
    if app_name == 'Slack':
        slack_count += 1

print('The number of times "Slack" appears in either data set:' , slack_count)
    

reviews_max = {}

for row in android_data[1:]:
    name = row[0]
    n_reviews = float(row[3])
    if name not in reviews_max:
        reviews_max[name] = n_reviews
    if name in reviews_max and reviews_max[name] < n_reviews:
        reviews_max[name] = n_reviews
        
    
print('The number of reviews for "Slack":', reviews_max['Slack'])
print('The number of unique entries:', len(reviews_max))

android_clean = []
already_added = []

for row in android_data[1:]:
    name = row[0]
    n_reviews = float(row[3])
    if reviews_max[name] == n_reviews and name not in already_added:
        android_clean.append(row)
        already_added.append(name)
        
print('The length of the android_clean data set:', len(android_clean))

print('\n')
for row in android_clean:
    if row[0] == 'Slack':
        print(row)

print('The total number of entries in the iOS data set:', len(ios_data))

ios_id_nums = []
for row in ios_data:
    if row[0] not in ios_id_nums:
        ios_id_nums.append(row[0])
    else:
        print('This ID number already exists:', row[0])
        
print('The total number of unique ID numbers in the iOS data set:', len(ios_id_nums))

string1 = 'Instagram'
string2 = '爱奇艺PPS -《欢乐颂2》电视剧热播'
string3 = 'Docs To Go™ Free Office Suite'
string4 = 'Instachat 😜'

def common_english_character(string):
    c_count = 0
    for character in string:
        if ord(character) > 127:
            c_count += 1
        if c_count == 3:
            return False
        

print(common_english_character(string1))
print(common_english_character(string2))
print(common_english_character(string3))
print(common_english_character(string4))

dataset = [ ['Instagram'], ['爱奇艺PPS -《欢乐颂2》电视剧热播'], ['Docs To Go™ Free Office Suite'], ['Instachat 😜']]
non_english_dataset = []

def common_english_character(dataset1, dataset2):
    for row in dataset:
        c_count = 0
        app_name = row[0]
        for character in app_name:
            if ord(character) > 127:
                c_count += 1
        if c_count >= 3:
            dataset1.remove(row)
            dataset2.append(row)
            
common_english_character(dataset, non_english_dataset)
print(dataset)
print(non_english_dataset)

non_english_android = []
dataset = android_clean

common_english_character(dataset, non_english_android)

print(len(non_english_android))
print(non_english_android[:5])
print(len(android_clean))
print(len(dataset))

non_english_ios = []

def cec_ios(dataset1, dataset2):
    for row in dataset:
        c_count = 0
        app_name = row[1]
        for character in app_name:
            if ord(character) > 127:
                c_count += 1
        if c_count >= 3:
            dataset1.remove(row)
            dataset2.append(row)
            
cec_ios(ios_data[1:], non_english_ios)

print(len(ios_data))
print(len(non_english_ios))

non_english_ios = []
dataset = ios_data[1:]

cec_ios(dataset, non_english_ios)

print(len(ios_data))
print(len(dataset))
print(len(non_english_ios))

extra = []

cec_ios(ios_data, extra)

print(len(ios_data))