#!/usr/bin/env python
# coding: utf-8

# # Mobile Apps
# 
# ## This Project is intended to ...

# In[1]:


opened_fileA = open("AppleStore.csv")
opened_fileG = open("googleplaystore.csv")

from csv import reader

read_fileA = reader(opened_fileA)
read_fileG = reader(opened_fileG)

apple = list(read_fileA)
google = list(read_fileG)

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]))


# In[2]:


explore_data(apple, 0, 6, True)

print("\n")
print("\n")

explore_data(google, 0, 6, True)


# In[3]:


explore_data(apple, 0, 1)

print("\n")

explore_data(google, 0, 1)


# In[4]:


print (google[0])
print (google[10473])


# In[5]:


for row in google:
    headerlen = len(google[0])
    
    if headerlen != len(row):
        print (row)
        print(google.index(row)) # prints the row index number


# In[6]:


for row in google:
    name = row[0]
    if name == 'Subway Surfers':
        print(row)

duplicate_apps = []
unique_apps = []

for row in google[1:]:
    name = row[0]
    if name in unique_apps:
        duplicate_apps.append(name)
    else:
        unique_apps.append(name)
        
print("Number of duplicate apps: ", len (duplicate_apps))
print("\n")
print("Examples of duplicate apps: ", duplicate_apps[:15])


# In[10]:


reviews_max = { }

for row in google[1:]:
    name = row[0]
    n_reviews = float(row[3])
    if name in reviews_max and reviews_max[name] < n_reviews:
        reviews_max.update( name = n_reviews )
    if name not in reviews_max:        
        reviews_max.update( {name: n_reviews} )

print (len(reviews_max))
print (reviews_max)


# google_clean = []
# already_added = []

# for row in google:
#     name = app[0]
#     n_reviews = float(app[0])
#     if n_reivews == 


# In[ ]: