srang992

# Navigate to your desired directory. Here I am using D
$ d:

# make the directory named 'ChromeCustomHomepage'
$ mkdir ChromeCustomHomepage

# Navigate to the newly created Directory
$ cd ChromeCustomHomepage

# install 'virtualenv' if you don't have it installed

srang992

# split those ingredients values
choco_data['ingredients'] = choco_data['ingredients'].str.strip(' ') 
choco_data['num_ingredients'] = choco_data['ingredients'].str.split('-', expand=True)[0] 
choco_data['main_ingredients'] = choco_data['ingredients'].str.split('-', expand=True)[1] 
choco_data['main_ingredients'] = choco_data['main_ingredients'].str.strip(' ') 

# encoding the values
ingre_encode = choco_data['main_ingredients'].str.get_dummies(sep=',')

# concatenating lecithin column with the main data. Containing lecithin denoted by 1 

srang992

# removing the misspelled word 
taste_codo['nutty'] = taste_codo['nut'] + taste_codo['nuts'] + taste_codo['nutty'] 
taste_codo['woody'] = taste_codo['woodsy'] + taste_codo['woody'] 
taste_codo['earthy'] = taste_codo['earth'] + taste_codo['earthy'] 
taste_codo.drop(['nut', 'nuts', 'woodsy', 'earth'], axis=1, inplace=True) 

# making the taste dictionary 
tasty_dict = {} 
tasty_list = list(taste_codo.columns) 
for taste in tasty_list: 

srang992

# filtering those chocolates which are manufactured by Soma Chocomaker 
soma_choco_data = choco_data[choco_data['manufacturer'].isin(['Soma'])] 

# creating the dictionary
bean_dict = {} 
bean_origins = list(soma_choco_data['bean_origin']) 
for origin in bean_origins: 
  if origin in bean_dict: 
    bean_dict[origin] += 1 
  else: 

srang992

# taking the all cocoa percentages uses in chocolates of soma chocomaker
cocoa_list = list(soma_choco_data['cocoa_percent']) 

# creating a dictionary
cocoa_percent_dict = {} 
for cocoa_percent in cocoa_list: 
  if str(cocoa_percent) in cocoa_percent_dict: 
    cocoa_percent_dict[str(cocoa_percent)] += 1 
  else: 
    cocoa_percent_dict[str(cocoa_percent)] = 1 

srang992

# removing those manufacturer whose count is less than 10
choco_data_with_sec_count = count_df(choco_data, 'manufacturer') 
choco_data_mod2 = choco_data_with_sec_count[choco_data_with_sec_count['count'] > 10] 

# grouping the data by manufacturer and calculating the avg. mean for each of them
avg_rating_by_company = choco_data_mod2.groupby('manufacturer')['rating'].mean() 
avg_rating_by_company_df = avg_rating_by_company.rename_axis('Company').reset_index(name='Rating') 
avg_rating_by_company_df_sorted = avg_rating_by_company_df.sort_values(by='Rating', ascending=False).head(10) 

# adding title and plotting the data

srang992

# listing all the tastes
tastes = list(taste_encode.columns) 
taste_dict = {}

# taking the sum of the values of those taste columns to understand how many people are agreed with that taste
for taste in tastes: 
  taste_dict[taste] = sum(taste_encode[taste]) 
  
# sorting the taste dictionary in decending order
taste_dict = sort_sliced_dict(taste_dict, is_reverse=True, item_count=8)

srang992

# filtering the taste of Kokoa Kamili and separating the values
taste_encode = choco_data[choco_data['bar_name'].isin(['Kokoa Kamili'])]['taste'].str.get_dummies(sep=', ') 

# fixing some of the values whose pronunciation is wrong
taste_encode['nuts'] = taste_encode['nut'] + taste_encode['nuts'] 
taste_encode['rich_cocoa'] = taste_encode['rich'] + taste_encode['rich cocoa'] + taste_encode['rich cooa']

# dropping the columns containing wrong pronunciation
taste_encode.drop(['nut', 'rich', 'rich cooa'], axis=1, inplace=True)

srang992

# filtering those companies where Kokoa Kamili is manufactured
company_loc_list = list(choco_data[choco_data['bar_name'].isin(['Kokoa Kamili'])]['company_loc'])
company_loc_dict = {i:company_loc_list.count(i) for i in company_loc_list}

# plotting the data
fig = px.pie(values=list(company_loc_dict.values()), 
             names=list(company_loc_dict.keys()), 
             title='Most Common Location where Kokoa Kamili is Manufactured', 
             color_discrete_sequence=px.colors.sequential.Aggrnyl) 

srang992

import plotly.express as px 
import plotly.graph_objects as go 

# removing those chocolates which has a count less than 10 
choco_data_with_count = count_df(choco_data, 'bar_name') 
choco_data_mod = choco_data_with_count[choco_data_with_count['count'] >= 10] 

# grouping chocolates according to bar_name and calculating mean 
avg_rating_by_bar = choco_data_mod.groupby('bar_name')['rating'].mean() 
avg_rating_by_bar_df = avg_rating_by_bar.rename_axis('bar_name').reset_index(name='rating')