from csv import reader
### The Google Play data set ###
# list(reader(open('googleplaystore.csv')))
opened_file = open('googleplaystore.csv')
read_file = reader(opened_file)
android = list(read_file)
android_header = android[0]
android_data = android[1:]
### The App Store data set ###
# list(reader(open('AppleStore.csv')))
opened_file = open('AppleStore.csv')
read_file = reader(opened_file)
iOS = list(read_file)
iOS_header = iOS[0]
iOS_data = iOS[1:]
def explore_data(dataset, start, end, rows_and_columns=False):
dataset_slice = dataset[start:end]
for row in dataset_slice:
print(row)
print('\n') # adds a new (empty) line after each row
if rows_and_columns:
print('Number of rows:', len(dataset))
print('Number of columns:', len(dataset[0]))
for row in android:
if len(row) != len(android_header):
print(row)
print(android.index(row))
print(android.index(row))
['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'] 10473 10841
print(len(android))
del(android[10473])
print(len(android))
print(android[10473])
10840 10839 ['Wi-Fi Visualizer', 'TOOLS', '3.9', '132', '2.6M', '50,000+', 'Free', '0', 'Everyone', 'Tools', 'May 17, 2017', '0.0.9', '2.3 and up']
unique_apps = []
duplicate_apps = []
for apps in android_data:
name = apps[0]
if name in unique_apps:
duplicate_apps.append(name)
else:
unique_apps.append(name)
print('Number of duplicate apps in Google Play Store is', len(duplicate_apps))
Number of duplicate apps in Google Play Store is 1181
for app in android:
if app[3] == '3.0M':
print(row)
print(android.index(row))
reviews_max = {}
for app in android_data:
name = app[0]
n_reviews = float(app[3])
if name in reviews_max and reviews_max[name] < n_reviews:
reviews_max[name] = n_reviews
elif name not in reviews_max:
reviews_max[name] = n_reviews
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-24-c4e974c7e427> in <module> 3 for app in android_data: 4 name = app[0] ----> 5 n_reviews = float(app[3]) 6 7 if name in reviews_max and reviews_max[name] < n_reviews: ValueError: could not convert string to float: '3.0M'