manmohan24nov

In [1]: import pandas as pd 
   ...: import numpy as np 
   ...: import matplotlib.pyplot as plt 
   ...: import seaborn as sns 
   ...: from collections import Counter 
    
 In [2]: sales_data = pd.read_csv('sales_data_set.csv')                                                                                                                  

In [3]: sales_data                                                                                                                                                      
Out[3]: 

manmohan24nov

In [2]: weekly_sales_df = sales_data[['Store', 
   ...:                               'Date', 
   ...:                               'Weekly_Sales']].groupby(['Store', 
   ...:                                                         'Date']).agg({'Weekly_Sales':'sum'})                                                                    

In [3]: weekly_sales_df.reset_index(inplace=True)                                                                                                                       

In [4]: weekly_sales_df['Date']= pd.to_datetime(weekly_sales_df['Date'])                                                                                                

In [5]: weekly_sales_df = weekly_sales_df.sort_values(by='Weekly_Sales',ascending=False)                                                                                

manmohan24nov

In [2]: sales_data_ordered = sales_data.sort_values(by=['Date'],ascending=False)                                                                                        

In [3]: sales_data_ordered['Date']= pd.to_datetime(sales_data_ordered['Date'])                                                                                          

In [5]: weekly_sales_df = sales_data_ordered[['Store', 
   ...:                               'Date', 
   ...:                               'Weekly_Sales']].groupby(['Store', 
   ...:                                                         'Date']).agg({'Weekly_Sales':'mean'})                                                                   

In [6]: weekly_sales_df.reset_index(inplace=True)                                                                                                                       

manmohan24nov

In [2]: weekly_sales_df = sales_data[['Store', 
   ...:                               'Date', 
   ...:                               'Weekly_Sales']].groupby(['Store', 
   ...:                                                         'Date']).agg({'Weekly_Sales':'mean'}) 

In [3]: weekly_sales_df.reset_index(inplace=True)

In [4]: weekly_sales_df['Percent_weekly_sales'] = weekly_sales_df.groupby(['Date'])['Weekly_Sales'].rank(pct=True, 
   ...:                                                                                      ascending=False)

manmohan24nov

In [3]: weekly_sales_df = sales_data[['Store', 
   ...:                               'Date', 
   ...:                               'Weekly_Sales']].groupby(['Date', 
   ...:                                                         'Store']).agg({'Weekly_Sales':'sum'})                                                                   

In [4]: weekly_sales_df.reset_index(inplace=True)                                                                                                                       

In [5]: weekly_sales_df['rank']=weekly_sales_df.groupby(['Store'])['Weekly_Sales'].rank(ascending=False) 
   ...: weekly_sales_df['dense_rank'] = weekly_sales_df.groupby(['Store'])['Weekly_Sales'].rank(method='dense',  
   ...:                                                                                      ascending=False)                                                           

manmohan24nov

# prtint min, max, median, first quartile, third quartile and random quartile
# using .quartile()
for i in num_col:
    print(f'Min: {train[i].quantile(0)} First Quartile: {train[i].quantile(0.25)}' 
          f'Median: {train[i].quantile(0.5)} Third Quartile: {train[i].quantile(0.75)}' 
          f'Max: {train[i].quantile(0)} Random Quartile(90%): {train[i].quantile(0.9)}')

# quartile for categorical variables
def percentile(n):
    def percentile_(x):

manmohan24nov

# import the 
import pandas as pd
from matplotlib import cm
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as patches
import matplotlib.path as path
import matplotlib.ticker as ticker
import matplotlib.animation as animation
import pandas as pd

manmohan24nov

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from collections import Counter

# Loat the train and test data
train_df = pd.read_csv('train.csv')
train_df['df_type'] = 'train'
test_df = pd.read_csv('test.csv')

manmohan24nov

import spacy	
from matplotlib import cm
from matplotlib.pyplot import plt

nlp = spacy.load('en_core_web_sm')
ner_collection = {"Location":[],"Person":[],"Date":[],"Quantity":[],"Organisation":[]}
location = []
person = []
date = []
quantity = []

manmohan24nov

from gensim.parsing.preprocessing 
import remove_stopwords					   
import genism											      
from wordcloud import WordCloud								   
import numpy as np										   
import random									          

# import stopwords from gensim methods to stop_list variable
# You can also manually add stopwords
gensim_stopwords = gensim.parsing.preprocessing.STOPWORDS