def get_computed_df(file_path, file, region):
file = file.split('.')[0]
df = pd.read_csv(file_path, sep='\t')
df['Query'] = file.split('--')[0]
# df['Query'] = df['Query'].str.replace('_',' ')
# Convert GMT to EST
date_time_stamp = file.split('--')[1].split('_showcase_ads')[0]
date_time_obj = datetime.strptime(date_time_stamp, "%d_%m_%Y__%H_%M_%S")
est_date_time_obj = date_time_obj - timedelta(hours=5)
df['Search Datetime'] = est_date_time_obj.strftime('%m-%d-%Y:%H:%M:%S')
column_list = df.columns.tolist()
for col in TITLE_CONVERSION_DICT.keys():
if col not in column_list:
df[col] = ''
for col in EXTRA_COLUMNS_FOR_SHOWCASE:
if col not in column_list:
df[col] = ''
df['Min Price'] = df['price'].apply(lambda x: x.split('-')[0])
df['Max Price'] = df['price'].apply(lambda x: x.split('-')[-1]
if '-' in x else '')
df['Store_Name'] = df['url'].apply(get_domain_url)
df.rename(columns=TITLE_CONVERSION_DICT, inplace=True)
total_product_count = len(df)
df['PLA Rank'] = range(1, total_product_count + 1)
df['Search Region'] = get_region_name(region)
df['PLA/Showcase'] = 'Showcase'
df['Search From'] = 'Mobile'
df = df[OUTPUT_COLUMN_LIST]
return df
def get_computed_df(self, file_path, file, region):
file = file.split('.')[0]
df = pd.read_csv(file_path, sep='\t')
df['Query'] = file.split('--')[0]
# df['Query'] = df['Query'].str.replace('_',' ')
# Convert GMT to EST
date_time_stamp = file.split('--')[1].split('_brands_related')[0]
date_time_obj = datetime.strptime(date_time_stamp, "%d_%m_%Y__%H_%M_%S")
est_date_time_obj = date_time_obj - timedelta(hours=5)
df['Search Datetime'] = est_date_time_obj.strftime('%m-%d-%Y:%H:%M:%S')
df['ASIN'] = df['url'].apply(lambda x: x.split('asins=')[1].split('&')[0] if type(x)!= float else x)
df.rename(columns=
{
'Query' : 'Search Keyword',
'text' : 'Brand Tagline',
'name' : 'Brand',
},
inplace=True)
total_product_count = len(df)
df['Result Rank'] = range(1, total_product_count+1)
df['Search Region'] = get_region_name(region)
df['Search From'] = 'Desktop'
df = df[OUTPUT_COLUMN_LIST]
return df
def get_computed_df(self, file_path, file, region):
file = file.split('.')[0]
df = pd.read_csv(file_path, sep='\t')
df['Query'] = file.split('--')[0]
df['Product Sponsored'] = 'Yes'
# df['Query'] = df['Query'].str.replace('_',' ')
# Convert GMT to EST
date_time_stamp = file.split('--')[1].split('_today_deals')[0]
date_time_obj = datetime.strptime(date_time_stamp, "%d_%m_%Y__%H_%M_%S")
est_date_time_obj = date_time_obj - timedelta(hours=5)
df['Search Datetime'] = est_date_time_obj.strftime('%m-%d-%Y:%H:%M:%S')
# df['rating'] = df['rating'].apply(lambda x: x.split(' ')[0].replace('(','').replace(')','') if type(x)!=float else x)
df['rating'] = df['rating'].apply(lambda x: x.split(' ')[0] if type(x)!=float else x)
df['total_ratings'] = df['total_ratings'].astype(str).fillna(value='')
df['total_ratings'] = df['total_ratings'].str.replace(',','')
# df['total_ratings'] = df['total_ratings'].str.replace('k+','000').str.replace('+','')
df['ASIN'] = df['url'].apply(lambda x: x.split('dp/')[1].split('/')[0])
df.rename(columns=
{
'Query' : 'Search Keyword',
'name' : 'Product Title',
'rating' : 'Product Ratings',
'total_ratings' : 'Product Reviews',
'sale_price' :'Product Sale Price',
'marked_price' : 'Product Marked Price',
'prime_info' : 'Product Is Prime',
'sale_price' : 'Product Sale Price',
'marked_price' : 'Product Marked Price'
},
inplace=True)
total_product_count = len(df)
df['Result Rank'] = range(1, total_product_count+1)
df['Search Region'] = get_region_name(region)
df['Search From'] = 'Desktop'
df = df[OUTPUT_COLUMN_LIST]
return df
def get_computed_df(self, file_path, file, region):
file = file.split('.')[0]
df = pd.read_csv(file_path, sep='\t')
df['Query'] = file.split('--')[0]
# df['Query'] = df['Query'].str.replace('_',' ')
# Convert GMT to EST
date_time_stamp = file.split('--')[1].split('_serp_result')[0]
date_time_obj = datetime.strptime(date_time_stamp, "%d_%m_%Y__%H_%M_%S")
est_date_time_obj = date_time_obj - timedelta(hours=5)
df['Search Datetime'] = est_date_time_obj.strftime('%m-%d-%Y:%H:%M:%S')
df['rating'] = df['rating'].apply(lambda x: x.split(' ')[0] if type(x)!=float else x)
df['total_ratings'] = df['total_ratings'].astype(str).fillna(value='')
df['total_ratings'] = df['total_ratings'].str.replace(',','')
df['ASIN'] = df['url'].apply(self.get_asin_from_url) # Redirection needed
df.rename(columns=
{
'Query' : 'Search Keyword',
'name' : 'Product Title',
'rating' : 'Product Ratings',
'total_ratings' : 'Product Reviews',
'sale_price' :'Product Sale Price',
'marked_price' : 'Product Marked Price',
'prime_info' : 'Product Is Prime',
'sponsored' : 'Product Sponsored',
'stock_info' : 'Product Stock Info',
'coupon_info' : 'Product Coupon Info',
'shipping_info' : 'Product Shipping Info',
'more_buy_info' : 'Product More Buy Info',
},
inplace=True)
total_product_count = len(df)
df['Result Rank'] = range(1, total_product_count+1)
df['Search Region'] = get_region_name(region)
df['Search From'] = 'Desktop'
df = df[OUTPUT_COLUMN_LIST]
return df
def get_computed_df(self, file_path, file, region):
file = file.split('.')[0]
df = pd.read_csv(file_path, sep='\t')
del df['image']
del df['return_policy']
df['url'] = df['url'].fillna(value='')
df['price'] = df['price'].fillna(value='')
df['review'] = df['review'].fillna(value='')
df['Query'] = file.split('--')[0]
# df['Query'] = df['Query'].str.replace('custom_t_shirts','Custom T-shirts').str.replace('men_s_shoes','Men\'s shoes').str.replace('red_sweater','Red Sweater')
# df['Query'] = df['Query'].str.replace('_',' ')
# Convert GMT to EST
date_time_stamp = file.split('--')[1].split('_sponsored_')[0]
date_time_obj = datetime.strptime(date_time_stamp, "%d_%m_%Y__%H_%M_%S")
est_date_time_obj = date_time_obj - timedelta(hours=5)
df['Search Datetime'] = est_date_time_obj.strftime('%m-%d-%Y:%H:%M:%S')
df['Store_Name'] = df['url'].apply(self.get_domain_url)
df['url'] = df['url'].apply(lambda x: x.split('?')[0] if 'google.com' in x and 'www.googleadservices.com/pagead/aclk' not in x else x)
df['price_drop'] = df['price_drop'].apply(lambda x: x.split('%')[0] if type(x)!=float else x)
df['Min Price'] = df['price'].apply(lambda x: x.split('-')[0])
df['Max Price'] = df['price'].apply(lambda x: x.split('-')[-1] if '-' in x else '')
df['rating'] = df['rating'].apply(lambda x: x.split(' ')[1] if type(x)!=float else x)
df['review'] = df['review'].apply(lambda x: x.split(' ')[0].replace('(','').replace(')','') if type(x)!=float else x)
df['review'] = df['review'].fillna(value='')
df['review'] = df['review'].str.replace('k+','000').str.replace('+','')
# df['price'] = df['price'].apply(self.get_range_price)
df.rename(columns=
{
'brand':'PLA Store',
'name': 'PLA Title',
'url' : 'PLA URL',
'price' : 'PLA Price Text',
'Min Price' : 'PLA Price MIN',
'Max Price' : 'PLA Price MAX',
'review' : 'PLA Reviews',
'rating' : 'PLA Ratings',
'price_drop' : 'PLA PriceDrop Percentage',
'Hour': 'Search Hour',
'Date': 'Search Date',
'Query': 'Search Keyword',
'PRICEC DROP TAG': 'PLA Has Price Drop Tag',
'SALE TAG': 'PLA Has Sale Tag',
'Store_Name': 'PLA Domain',
'In Store/Pick up Today' : 'PLA Has Special Tags'
},
inplace=True)
total_product_count = len(df)
df['PLA Rank'] = range(1, total_product_count+1)
df['Search Region'] = get_region_name(region)
df['PLA/Showcase'] = 'PLA'
df['Search From'] = 'Desktop'
df = df[df['PLA URL']!='']
df = df[self.output_column_list]
return df
