aniruddha27

#new revenue column 
df['revenue'] = df.apply(lambda x: x.checkout_price*x.num_orders,axis=1) 

#new month column 
df['month'] = df['week'].apply(lambda x: x//4) 

#list to store month-wise revenue 
month=[] 
month_order=[] 

aniruddha27

center_type_name = ['TYPE_A','TYPE_B','TYPE_C'] 

#relation between op area and number of orders 
op_table=pd.pivot_table(df,index='op_area',values='num_orders',aggfunc=np.sum) 

#relation between center type and op area 
c_type = {} 
for i in center_type_name: 
    c_type[i] = df[df['center_type']==i].op_area 

aniruddha27

import pandas as pd 
import numpy as np 
import matplotlib.pyplot as plt 
plt.style.use('seaborn')

aniruddha27

df_meal = pd.read_csv('C:\\Users\Dell\\Desktop\\train_food\\meal_info.csv') 
df_meal.head()

aniruddha27

df_center = pd.read_csv('C:\\Users\Dell\\Desktop\\train_food\\fulfilment_center_info.csv') 
df_center.head()

aniruddha27

train = pd.read_csv('/kaggle/input/house-prices-advanced-regression-techniques/train.csv')
test = pd.read_csv('/kaggle/input/house-prices-advanced-regression-techniques/test.csv')

aniruddha27

train.head()

aniruddha27

train.info()

aniruddha27

train['SalePrice'].describe()

aniruddha27

import seaborn as sns
sns.distplot(train['SalePrice'])
plt.xticks(rotation=30);