API tools faq
paste
George_Zagorsky_1

Untitled

George_Zagorsky_1
Mar 9th, 2022
104
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 22.26 KB | None | 0 0
raw download clone embed print report
  1. import pandas
  2.  
  3.  
  4. def rename_columns(csv_file):  # fuction to rename bad columns
  5.     csv_file = csv_file.rename(
  6.         columns={'Price $': 'Price', 'FBA Fees $': 'FBA_Fees', 'Active Sellers #': 'Active_Sellers',
  7.                  'Product Details': 'Product_Details', 'Review Count': 'Review_Count',
  8.                  'Review velocity': 'Review_velocity', 'Buy Box': 'Buy_Box', 'Size Tier': 'Size_Tier',
  9.                  'Creation Date': 'Creation_Date'})
  10.  
  11.     return csv_file
  12.  
  13.  
  14. def drop_all_duplicates(csv_file):
  15.     csv_file = csv_file.drop_duplicates().reset_index(drop=True)
  16.     return csv_file
  17.  
  18.  
  19. def rename_words(csv):  # fuction to rename all NANS to 'UNKNOWN'
  20.     list = sum(csv.isna().sum())
  21.     if list != 0:
  22.         for element in csv.columns:
  23.             csv[element] = csv[element].fillna('UNKNOWN')
  24.     return csv
  25.  
  26.  
  27. def remove_all_commas(csv_file):  # fucnction to remove all commas from csv file
  28.     array = ['Price', 'Sales', 'Revenue', 'Review_Count', 'Review_velocity', 'BSR', 'FBA_Fees', 'Active_Sellers',
  29.              'Images', 'Weight']
  30.     data_frame = pandas.DataFrame(csv_file)
  31.     for element in array:
  32.         i = 0
  33.         for el in data_frame[element]:
  34.             answer = ''
  35.             stack = []
  36.             if type(el) == str:
  37.                 if el != 'UNKNOWN':
  38.                     if ',' in el:
  39.                         for new_el in el:
  40.                             if new_el.isdigit() or new_el == '.':
  41.                                 stack.append(new_el)
  42.                             else:
  43.                                 continue
  44.                         for key in stack:
  45.                             answer += key
  46.                         if element in ['Sales', 'Review_Count']:
  47.                             data_frame.loc[i, element] = int(answer)
  48.                             i += 1
  49.                         else:
  50.  
  51.                             data_frame.loc[i, element] = float(answer)
  52.                             i += 1
  53.                     else:
  54.                         if element in ['Sales', 'Review_Count']:
  55.                             result = int(el)
  56.                             data_frame.loc[i, element] = result
  57.                             i += 1
  58.                         else:
  59.                             result = float(el)
  60.                             data_frame.loc[i, element] = result
  61.                             i += 1
  62.  
  63.  
  64.  
  65.  
  66.             else:
  67.                 i += 1
  68.  
  69.     return data_frame
  70.  
  71.  
  72. def check_the_types(csv_file):  # have already yet
  73.     for element in csv_file.columns:
  74.         for el in csv_file[element]:
  75.             print(el, ' ', type(el))
  76.     return f'All types from all csv_file : {csv_file}'
  77.  
  78.  
  79. def remove_commas_test(csv_file):  # bad function for  future test
  80.     pass
  81.  
  82.  
  83. def convet_to_csv(data_frame):  # Fucton to convert data_frame as csv
  84.     csv_file = data_frame.to_csv('tested_file_for_amazon.csv')
  85.  
  86.     return csv_file
  87.  
  88.  
  89. def convert_revenue_to_int(csv_file):
  90.     index = 0
  91.     for element in list(csv_file['Revenue']):
  92.         if csv_file.loc[index, 'Revenue'] != 'UNKNOWN':
  93.             csv_file.loc[index, 'Revenue'] = int(csv_file.loc[index, 'Revenue'])
  94.         index += 1
  95.     return csv_file
  96.  
  97.  
  98. def remove_unknown_from_Revenue(csv_file):
  99.     index = 0
  100.     for element in list(csv_file['Revenue']):
  101.         if element == 'UNKNOWN':
  102.             csv_file.loc[index, 'Revenue'] = 0
  103.         index += 1
  104.  
  105.     return csv_file
  106.  
  107.  
  108. def sort_revenue(data_frame):  # test
  109.     data_frame = data_frame.sort_values('Revenue', ascending=False)
  110.     return data_frame
  111.  
  112.  
  113. def check_types_of_str_columns(csv_file):  # another fuction to check types
  114.     stack_of_columns = ['Price', 'Sales', 'Revenue', 'Review_Count', 'Review_velocity', 'BSR', 'FBA_Fees']
  115.     for name_of_column in stack_of_columns:
  116.         for element in csv_file[name_of_column]:
  117.             if type(element) == str:
  118.                 continue
  119.             else:
  120.                 print(f'The tipy of element is: {type(element)} and the element is : {element}')
  121.                 if type(element) == str:
  122.                     raise Exception
  123.  
  124.  
  125. def check_test(csv_file):  # fuction to understand types
  126.     for element in csv_file.columns:
  127.         for el in csv_file[element]:
  128.             print(el, ' ', type(el))
  129.     return False
  130.  
  131.  
  132. def find_sum_column_sales(csv_file):  # Find sum of sales column
  133.     result = 0
  134.     for element in list(csv_file['Sales']):
  135.         if element != 'UNKNOWN':
  136.             result += int(element)
  137.     return result
  138.  
  139.  
  140. def find_sum_of_revenue_column(csv_file):  # Find sum of Revenue
  141.     result = 0
  142.     for element in list(csv_file['Revenue']):
  143.         if element != 'UNKNOWN':
  144.             result += int(element)
  145.     return result
  146.  
  147.  
  148. def find_sum_of_price(csv_file):  # Find sum of Price column
  149.     result = 0
  150.     for element in list(csv_file['Price']):
  151.         if element != 'UNKNOWN':
  152.             result += int(element)
  153.  
  154.     return result
  155.  
  156.  
  157. def find_sum_of_review_count(csv_file):  # Find sum of Review_Count column
  158.     result = 0
  159.     for element in list(csv_file['Review_Count']):
  160.         result += int(element)
  161.  
  162.     return result
  163.  
  164.  
  165. def convert_unkown_to_digit_if_needed(csv_file):  # Function for future math - to rename all String to zero
  166.     stack_of_columns = ['Price', 'Sales', 'Revenue', 'Review_Count', 'Ratings', 'Review_velocity', 'BSR', 'FBA_Fees',
  167.                         'Active_Sellers']
  168.     for name in stack_of_columns:
  169.         i = 0
  170.         for element in csv_file[name]:
  171.             if type(element) == str:
  172.                 csv_file[name][i] = 0
  173.             i += 1
  174.  
  175.     return csv_file
  176.  
  177.  
  178. def work_with_columns(csv_file):  # Find sum of Revenue Column - second - for the most reason
  179.     counter = 0
  180.     for element in csv_file['Revenue']:
  181.         counter += element
  182.  
  183.     return counter
  184.  
  185.  
  186. def create_sample():  # create sample for future csv
  187.     rows_for_csv = [
  188.         ['Face_Mask', 0, 0, 0, 0, 0, 0, 0, 0, ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' '],
  189.         [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', 'GR1', 'GR2',
  190.          'GR3', 'REST', '0-99', '100-499', '500-999', '1000'],
  191.         [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '(1-3) G1R', '(4-9) G2R', '(10-16) G3R', '(16-58) G4R',
  192.          '(1-3) G1AR', '(4-9) G2AR', '(10-16) G3AR', '(16-58) G4AR', 0, 0, 0, 0, 0, 0, 0, 0],
  193.         [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', 0, 0, 0, 0, 0, 0, 0, 0, ' ', ' ', ' ', ' ', ' ', ' ', ' ',
  194.          ' '],
  195.         [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', '(1-3) G1RW', '(4-9) G2RW', '(10-16) G3RW',
  196.          '(16-58) G4RW', '(1-3) G1ARW', '(4-9) G2ARW', '(10-16) G3ARW', '(16-58) G4ARW', ' ', ' ', ' ', ' ', 0,
  197.          0, 0, 0],
  198.         [' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', 0, 0, 0, 0, 0, 0, 0, 0, ' ', ' ', ' ', ' ', ' ', ' ', ' ',
  199.          ' ']
  200.     ]
  201.     columns_for_csv = ['Product', 'Main_Search_Terms', 'Revenue', 'Avg. Reviews', 'Review per Revenue (RPR)',
  202.                        'Sales (GR1, GR2, GR3)', 'Review Velocity (GR1, GR2, GR3)', 'Review CVR (GR1, GR2, GR3)',
  203.                        'Products per Page', 'GxR / GxRW', '1', '2', '3', 'GxAR / GxARW', '4', '5',
  204.                        '6',
  205.                        'Groups Share', '7', '8', '9',
  206.                        '\tAvg. Revenue for Groups by Reviews and Listings Count',
  207.                        '10', '11', '12']
  208.  
  209.     data_frame = pandas.DataFrame(data=rows_for_csv, columns=columns_for_csv)
  210.     return data_frame
  211.  
  212.  
  213. def check_types(csv_file):  # have allready done
  214.     for element in csv_file.columns:
  215.         for el in csv_file[element]:
  216.             print(el, ' : ', type(el))
  217.     pass
  218.  
  219.  
  220. def find_revenue_sum(data_frame_sample, csv_file_as_data_frame):
  221.     stack = [element for element in list(csv_file_as_data_frame['Revenue']) if element != 'UNKNOWN']
  222.     result_sum = sum(stack)
  223.     data_frame_sample.loc[0, 'Revenue'] = int(result_sum)
  224.     return data_frame_sample
  225.  
  226.  
  227. def find_sum_of_revenue_columns(csv_file, sample_of_data_frame):
  228.     summa = int(sum([x for x in list(csv_file['Revenue']) if x != 'UNKNOWN']))
  229.  
  230.     sample_of_data_frame.loc[0, 'Revenue'] = summa
  231.     pass
  232.  
  233.  
  234. def find_mean_avg_reviews(csv_file, sample_of_data_frame):  # ?
  235.     summa = int(sum([x for x in list(csv_file['Review_Count']) if x != 'UNKNOWN']))
  236.     length = len([x for x in list(csv_file['Review_Count']) if x != 'UNKNOWN'])
  237.     mean = summa / length
  238.     sample_of_data_frame.loc[0, 'Avg. Reviews'] = int(mean)
  239.     return sample_of_data_frame
  240.  
  241.  
  242. def review_per_revenue(sample_data_frame):
  243.     sample_data_frame.loc[0, 'Review per Revenue (RPR)'] = int(
  244.         sample_data_frame.loc[0, 'Revenue'] / sample_data_frame.loc[
  245.             0, 'Avg. Reviews'])
  246.     return sample_data_frame
  247.  
  248.  
  249. def find_sum_of_sales(csv_file, sample_of_data_frame):  # proverit' na real case
  250.     stack = csv_file['Sales'][0:16]
  251.     filtered_array = [x for x in stack if x != 'UNKNOWN']
  252.     sample_of_data_frame.loc[0, 'Sales (GR1, GR2, GR3)'] = sum(filtered_array)
  253.     return sample_of_data_frame
  254.  
  255.  
  256. def find_sum_review_velocity(sample_data_frame, csv_file):
  257.     array_of_velocity = csv_file['Review_velocity'][0:16]
  258.     array_of_velocity = [x for x in array_of_velocity if x != 'UNKNOWN']
  259.     sample_data_frame.loc[0, 'Review Velocity (GR1, GR2, GR3)'] = sum(array_of_velocity)
  260.     return sample_data_frame
  261.  
  262.  
  263. def find_percent_velocity_sales(sample_data_frame):
  264.     result = (sample_data_frame.loc[0, 'Review Velocity (GR1, GR2, GR3)'] / sample_data_frame.loc[
  265.         0, 'Sales (GR1, GR2, GR3)']) * 100
  266.     result = str(result)
  267.     stack = []
  268.     counter = 0
  269.     for element in result:
  270.         stack.append(element)
  271.         counter += 1
  272.         if counter == 4:
  273.             break
  274.     answer = ''
  275.     for element in stack:
  276.         answer += element
  277.     sample_data_frame.loc[0, 'Review CVR (GR1, GR2, GR3)'] = answer + '%'
  278.     return sample_data_frame
  279.  
  280.  
  281. def product_pet_page(csv_file, sample_data_frame):
  282.     lenght = len(csv_file)
  283.     sample_data_frame.loc[0, 'Products per Page'] = lenght
  284.     return sample_data_frame
  285.  
  286.  
  287. def find_avg_review(csv_file, data_frame):
  288.     stack_of_revenue = csv_file['Revenue'][0:3]
  289.     filtered_array = [x for x in stack_of_revenue if x != 'UNKNOWN']
  290.     result_sum = sum(filtered_array)
  291.     length = len(filtered_array)
  292.     data_frame.loc[3, 'GxAR / GxARW'] = str(int(result_sum / length)) + '$'
  293.     return data_frame
  294.  
  295.  
  296. def find_sum_group_1_3(csv_file, sample_data_frame):
  297.     stack_of_revenue = csv_file['Revenue'][0:3]
  298.     filtered_array = [x for x in stack_of_revenue if x != 'UNKNOWN']
  299.     result_sum = sum(filtered_array)
  300.     sample_data_frame.loc[3, 'GxR / GxRW'] = str(int(result_sum)) + '$'
  301.     return sample_data_frame
  302.  
  303.  
  304. def csv_file_to_data_frame_and_back(csv_file):
  305.     data_frame = pandas.DataFrame(csv_file)
  306.     realod_csv = data_frame.to_csv('for_boys_answers.csv')
  307.     return realod_csv
  308.  
  309.  
  310. def find_avg_second_review(csv_file, data_frame):
  311.     stack_of_group = csv_file['Revenue'][3:9]
  312.     filtered_array = [x for x in stack_of_group if x != 'UNKNOWN']
  313.     result_sum = sum(filtered_array)
  314.     length = len(filtered_array)
  315.     data_frame.loc[3, '4'] = str(int(result_sum / length)) + '$'
  316.     return data_frame
  317.  
  318.  
  319. def find_sum_group_4_9(csv_file, sample_data_frame):
  320.     stack_of_group = csv_file['Revenue'][3:9]
  321.     filtered_array = [x for x in stack_of_group if x != 'UNKNOWN']
  322.     result_sum = sum(filtered_array)
  323.     sample_data_frame.loc[3, '1'] = str(int(result_sum)) + '$'
  324.     return sample_data_frame
  325.  
  326.  
  327. def find_third_revenue_avg(csv_file, data_frame):
  328.     stack_group = csv_file['Revenue'][9:16]
  329.     filtered_array = [x for x in stack_group if x != 'UNKNOWN']
  330.     result_sum = sum(filtered_array)
  331.     length = len(filtered_array)
  332.     data_frame.loc[3, '5'] = str(int(result_sum / length)) + '$'
  333.     return data_frame
  334.  
  335.  
  336. def find_sum_revenue_10_16(csv_file, sample_data_frame):
  337.     stack_group = csv_file['Revenue'][9:16]
  338.     filtered_array = [x for x in stack_group if x != 'UNKNOWN']
  339.     result_sum = sum(filtered_array)
  340.     sample_data_frame.loc[3, '2'] = str(int(result_sum)) + '$'
  341.     return sample_data_frame
  342.  
  343.  
  344. def find_fourth_avg_reviews(csv_file, data_frame):
  345.     stack_group = csv_file['Revenue'][16:len(csv_file)]
  346.     filtered_array = [x for x in stack_group if x != 'UNKNOWN']
  347.     result_sum = sum(filtered_array)
  348.     length = len(filtered_array)
  349.     data_frame.loc[3, '6'] = str(int(result_sum / length)) + '$'
  350.     return data_frame
  351.  
  352.  
  353. def find_sum_17_to_last(csv_file, sample_data_frame):
  354.     stack_group = csv_file['Revenue'][16:len(csv_file)]
  355.     filtered_array = [x for x in stack_group if x != 'UNKNOWN']
  356.     result_sum = sum(filtered_array)
  357.     sample_data_frame.loc[3, '3'] = str(int(result_sum)) + '$'
  358.     return sample_data_frame
  359.  
  360.  
  361. def find_avg_review_count_1(csv_file, data_frame):
  362.     stack_review_count = csv_file['Review_Count'][0:3]
  363.     filtered_stack = [x for x in stack_review_count if x != 'UNKNOWN']
  364.     result_sum = sum(filtered_stack)
  365.     length = len(filtered_stack)
  366.     data_frame.loc[5, 'GxAR / GxARW'] = str(int(result_sum / length))
  367.     return data_frame
  368.  
  369.  
  370. def find_sum_review_count_1_3(csv_file, sample_data_frame):
  371.     stack_review_count = csv_file['Review_Count'][0:3]
  372.     filtered_stack = [x for x in stack_review_count if x != 'UNKNOWN']
  373.     result_sum = sum(filtered_stack)
  374.     sample_data_frame.loc[5, 'GxR / GxRW'] = int(result_sum)
  375.     return sample_data_frame
  376.  
  377.  
  378. def find_avg_review_count_2(csv_file, data_frame):
  379.     stack = csv_file['Review_Count'][3:9]
  380.     filtered_stack = [x for x in stack if x != 'UNKNOWN']
  381.     sum_result = sum(filtered_stack)
  382.     length = len(filtered_stack)
  383.     data_frame.loc[5, '4'] = str(int(sum_result / length))
  384.     return data_frame
  385.  
  386.  
  387. def find_sum_review_count_4_9(csv_file, sample_data_frame):
  388.     stack = csv_file['Review_Count'][3:9]
  389.     filtered_stack = [x for x in stack if x != 'UNKNOWN']
  390.     sum_result = sum(filtered_stack)
  391.     sample_data_frame.loc[5, '1'] = int(sum_result)
  392.     return sample_data_frame
  393.  
  394.  
  395. def find_avg_review_count_3(csv_file, data_frame):
  396.     filtered_stack = [x for x in list(csv_file['Review_Count'][9:16]) if x != 'UNKNOWN']
  397.     sum_result = sum(filtered_stack)
  398.     length = len(filtered_stack)
  399.     data_frame.loc[5, '5'] = str(int(sum_result / length))
  400.     return data_frame
  401.  
  402.  
  403. def find_sum_review_count_10_16(csv_file, sample_data_frame):
  404.     filtered_stack = [x for x in list(csv_file['Review_Count'][9:16]) if x != 'UNKNOWN']
  405.     sum_result = sum(filtered_stack)
  406.     sample_data_frame.loc[5, '2'] = int(sum_result)
  407.     return sample_data_frame
  408.  
  409.  
  410. def find_avg_review_count_4(csv_file, data_frame):
  411.     stack_review_count = csv_file['Review_Count'][16:len(csv_file)]
  412.     filtered_array = [x for x in stack_review_count if x != 'UNKNOWN']
  413.     result_sum = sum(filtered_array)
  414.     length = len(filtered_array)
  415.     data_frame.loc[5, '6'] = str(int(result_sum / length))
  416.     return data_frame
  417.  
  418.  
  419. def find_sum_review_count_16_last(csv_file, sample_data_frame):
  420.     stack_review_count = csv_file['Review_Count'][16:len(csv_file)]
  421.     filtered_array = [x for x in stack_review_count if x != 'UNKNOWN']
  422.     result_sum = sum(filtered_array)
  423.     sample_data_frame.loc[5, '3'] = int(result_sum)
  424.     return sample_data_frame
  425.  
  426. def remove_dollar_from_revenue_groups(data_frame):
  427.     stack_of_replacement = ['GxR / GxRW', '1', '2', '3']
  428.     for element in stack_of_replacement:
  429.         data_frame.loc[3, element] = data_frame.loc[3, element].replace('$', '')
  430.     return data_frame
  431.  
  432.  
  433. def replace_type_revenue_groups(data_frame):
  434.     stack_of_replacement = ['GxR / GxRW', '1', '2', '3']
  435.     for element in stack_of_replacement:
  436.         data_frame.loc[3, element] = int(data_frame.loc[3, element])
  437.  
  438.     return data_frame
  439.  
  440.  
  441. def all_types_review_count_to_int(csv_file):
  442.     stack = ['Review_Count']
  443.     counter = 0
  444.     for element in stack:
  445.         for el in csv_file[element]:
  446.             csv_file.loc[counter, element] = int(csv_file.loc[counter, element])
  447.  
  448.     return csv_file
  449.  
  450.  
  451. def sort_for_review_count(csv_file):
  452.     csv_file = csv_file.sort_values('Review_Count', ascending = False)
  453.     return csv_file
  454.  
  455. def find_sum_from_zero_to_hundred(csv_file, data_frame):
  456.     new_csv = csv_file[csv_file['Review_Count'] < 100]
  457.     filtered_array = [x for x in list(new_csv['Revenue']) if x != 'UNKNOWN']
  458.     result_sum = sum(filtered_array)
  459.     data_frame.loc[2, 'Avg. Revenue for Groups by Reviews and Listings Count'] = int(result_sum)
  460.     return data_frame
  461.  
  462.  
  463. def find_sum_from_hundred_to_5_hundred(csv_file, data_frame):
  464.     new_csv = csv_file[csv_file['Review_Count'] > 100]
  465.     new_csv = new_csv[new_csv['Review_Count'] < 500]
  466.     filtered_array = [x for x in list(new_csv['Revenue']) if x != 'UNKNOWN']
  467.     result_sum = sum(filtered_array)
  468.     data_frame.loc[2, '10'] = int(result_sum)
  469.     return data_frame
  470.  
  471. def find_sum_from_5_hundred_to_1_thousand(csv_file, data_frame):
  472.     new_csv = csv_file[csv_file['Review_Count'] < 1000]
  473.     new_csv = new_csv[new_csv['Review_Count'] > 500]
  474.     filtered_array = [x for x in list(new_csv['Revenue']) if x != 'UNKNOWN']
  475.     result_sum = sum(filtered_array)
  476.     data_frame.loc[2, '11'] = int(result_sum)
  477.     return data_frame
  478.  
  479. def find_sum_more_than_thousand(csv_filem, data_frame):
  480.     new_csv = csv_filem[csv_filem['Review_Count'] > 1000]
  481.     filtered_array = [x for x in list(new_csv['Revenue']) if x != 'UNKNOWN']
  482.     result_sum = sum(filtered_array)
  483.     data_frame.loc[2, '12'] = int(result_sum)
  484.     return data_frame
  485.  
  486. def groups_share_1(data_frame):
  487.     #formula : GxR / sum(revenue) * 100
  488.     first_group = data_frame.loc[3, 'GxR / GxRW']
  489.     result_sum = data_frame.loc[0, 'Revenue']
  490.     data_frame.loc[2, 'Groups Share'] = str(int((first_group / result_sum) * 100)) + '%'
  491.     return data_frame
  492.  
  493. def groups_share_2(data_frame):
  494.     second_group = data_frame.loc[3, '1']
  495.     result_sum = data_frame.loc[0, 'Revenue']
  496.     data_frame.loc[2, '7'] = str(int((second_group / result_sum) * 100)) + '%'
  497.     return data_frame
  498.  
  499.  
  500. def groups_share_3(data_frame):
  501.     third_group = data_frame.loc[3, '2']
  502.     result_sum = data_frame.loc[0, 'Revenue']
  503.     data_frame.loc[2, '8'] = str(int((third_group / result_sum) * 100 )) + '%'
  504.     return data_frame
  505.  
  506. def groups_share_delta(data_frame):
  507.     delta_group = data_frame.loc[3, '6']
  508.     result_sum = data_frame.loc[0, 'Revenue']
  509.     data_frame.loc[2, '9'] = str(int((delta_group / result_sum) * 100)) + '%'
  510.     return data_frame
  511.  
  512.  
  513.  
  514.  
  515. def length_reviews_0_99(csv_file, data_frame):
  516.     new_csv = csv_file[csv_file['Review_Count'] < 100]
  517.     length = len(new_csv)
  518.     data_frame.loc[4, '\tAvg. Revenue for Groups by Reviews and Listings Count'] = length
  519.     return data_frame
  520.  
  521. def lenth_reviews_100_500(csv_file, data_frame):
  522.     new_csv = csv_file[csv_file['Review_Count'] > 100]
  523.     new_csv = new_csv[new_csv['Review_Count'] < 500]
  524.     length = len(new_csv)
  525.     data_frame.loc[4, '10'] = length
  526.     return data_frame
  527.  
  528.  
  529. def length_reviews_500_1000(csv_file, data_frame):
  530.     new_csv = csv_file[csv_file['Review_Count'] > 500]
  531.     new_csv = new_csv[new_csv['Review_Count'] < 1000]
  532.     data_frame.loc[4, '11'] = len(new_csv)
  533.     return data_frame
  534.  
  535.  
  536. def length_reviews_more_then_thousand(csv_file, data_frame):
  537.     new_csv = csv_file[csv_file['Review_Count'] > 1000]
  538.     length = len(new_csv)
  539.     data_frame.loc[4, '12'] = length
  540.     return data_frame
  541.  
  542.  
  543. def swap_int_to_str_groups(data_frame):
  544.     stack_of_groups = ['GxR / GxRW', '1', '2', '3']
  545.     for element in stack_of_groups:
  546.         data_frame.loc[3, element] = str(data_frame.loc[3, element]) + '%'
  547.     return data_frame
  548.  
  549.  
  550. def remove_all_digits_from_columns(data_frame):
  551.     data_frame = data_frame.rename(columns = {'1' : ' ', '2' : ' ', '3' : ' ', '4' : ' ', '5' : ' ', '6' : ' ', '7' : ' ', '8' : ' ', '9' : ' ', '10' : ' ', '11' : ' ', '12' : ' '})
  552.     return data_frame
  553.  
  554.  
  555. def swap_int_to_str(data_frame):
  556.     data_frame.loc[0, 'Revenue'] = str(data_frame.loc[0, 'Revenue']) + '$'
  557.     return data_frame
  558.  
  559.  
  560.  
  561.  
  562.  
  563.  
  564.  
  565. if __name__ == '__main__':
  566.     file_for_amazon_csv = pandas.read_csv('"D:\naruto\Helium_10_Xray_2022-02-12.csv"')
  567.     file_for_amazon_csv = pandas.DataFrame(file_for_amazon_csv)  # test
  568.     file_for_amazon_csv = rename_columns(file_for_amazon_csv)
  569.     file_for_amazon_csv = drop_all_duplicates(file_for_amazon_csv)
  570.     file_for_amazon_csv = rename_words(file_for_amazon_csv)
  571.     file_for_amazon_csv = remove_all_commas(file_for_amazon_csv)
  572.     file_for_amazon_csv = convert_revenue_to_int(file_for_amazon_csv)
  573.     file_for_amazon_csv = remove_unknown_from_Revenue(file_for_amazon_csv)
  574.     file_for_amazon_csv = sort_revenue(file_for_amazon_csv)
  575.     data_frame = create_sample()
  576.     data_frame = find_revenue_sum(data_frame, file_for_amazon_csv)
  577.     data_frame = find_mean_avg_reviews(file_for_amazon_csv, data_frame)
  578.     data_frame = review_per_revenue(data_frame)
  579.     data_frame = find_sum_of_sales(file_for_amazon_csv, data_frame)
  580.     data_frame = find_sum_review_velocity(data_frame, file_for_amazon_csv)
  581.     data_frame = find_percent_velocity_sales(data_frame)
  582.     data_frame = product_pet_page(file_for_amazon_csv, data_frame)
  583.     data_frame = find_sum_group_1_3(file_for_amazon_csv, data_frame)
  584.     data_frame = find_sum_group_4_9(file_for_amazon_csv, data_frame)
  585.     data_frame = find_sum_revenue_10_16(file_for_amazon_csv, data_frame)
  586.     data_frame = find_sum_17_to_last(file_for_amazon_csv, data_frame)
  587.     data_frame = find_sum_review_count_1_3(file_for_amazon_csv, data_frame)
  588.     data_frame = find_sum_review_count_4_9(file_for_amazon_csv, data_frame)
  589.     data_frame = find_sum_review_count_10_16(file_for_amazon_csv, data_frame)
  590.     data_frame = find_sum_review_count_16_last(file_for_amazon_csv, data_frame)
  591.     data_frame = find_avg_review(file_for_amazon_csv, data_frame)
  592.     data_frame = find_avg_second_review(file_for_amazon_csv, data_frame)
  593.     data_frame = find_third_revenue_avg(file_for_amazon_csv, data_frame)
  594.     data_frame = find_fourth_avg_reviews(file_for_amazon_csv, data_frame)
  595.     data_frame = find_avg_review_count_1(file_for_amazon_csv, data_frame)
  596.     data_frame = find_avg_review_count_2(file_for_amazon_csv, data_frame)
  597.     data_frame = find_avg_review_count_3(file_for_amazon_csv, data_frame)
  598.     data_frame = find_avg_review_count_4(file_for_amazon_csv, data_frame)
  599.     file_for_amazon_csv = convet_to_csv(data_frame)
  600.  
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!