In [ ]:

    

# Get data here: https://datahack.analyticsvidhya.com/contest/practice-problem-big-mart-sales-iii/


    

In [1]:

    

import pandas as pd
import numpy as np
from catboost import CatBoostRegressor


train = pd.read_csv("train.csv")
test = pd.read_csv("test.csv")


    

In [2]:

    

train.head()


    

    
Out[2]:







  

    

      

      
Item_Identifier
      
Item_Weight
      
Item_Fat_Content
      
Item_Visibility
      
Item_Type
      
Item_MRP
      
Outlet_Identifier
      
Outlet_Establishment_Year
      
Outlet_Size
      
Outlet_Location_Type
      
Outlet_Type
      
Item_Outlet_Sales
    
  
  

    

      
0
      
FDA15
      
9.30
      
Low Fat
      
0.016047
      
Dairy
      
249.8092
      
OUT049
      
1999
      
Medium
      
Tier 1
      
Supermarket Type1
      
3735.1380
    
    

      
1
      
DRC01
      
5.92
      
Regular
      
0.019278
      
Soft Drinks
      
48.2692
      
OUT018
      
2009
      
Medium
      
Tier 3
      
Supermarket Type2
      
443.4228
    
    

      
2
      
FDN15
      
17.50
      
Low Fat
      
0.016760
      
Meat
      
141.6180
      
OUT049
      
1999
      
Medium
      
Tier 1
      
Supermarket Type1
      
2097.2700
    
    

      
3
      
FDX07
      
19.20
      
Regular
      
0.000000
      
Fruits and Vegetables
      
182.0950
      
OUT010
      
1998
      
NaN
      
Tier 3
      
Grocery Store
      
732.3800
    
    

      
4
      
NCD19
      
8.93
      
Low Fat
      
0.000000
      
Household
      
53.8614
      
OUT013
      
1987
      
High
      
Tier 3
      
Supermarket Type1
      
994.7052
    
  

In [3]:

    

train.dtypes


    

    
Out[3]:





Item_Identifier               object
Item_Weight                  float64
Item_Fat_Content              object
Item_Visibility              float64
Item_Type                     object
Item_MRP                     float64
Outlet_Identifier             object
Outlet_Establishment_Year      int64
Outlet_Size                   object
Outlet_Location_Type          object
Outlet_Type                   object
Item_Outlet_Sales            float64
dtype: object

In [4]:

    

train.isnull().sum()


    

    
Out[4]:





Item_Identifier                 0
Item_Weight                  1463
Item_Fat_Content                0
Item_Visibility                 0
Item_Type                       0
Item_MRP                        0
Outlet_Identifier               0
Outlet_Establishment_Year       0
Outlet_Size                  2410
Outlet_Location_Type            0
Outlet_Type                     0
Item_Outlet_Sales               0
dtype: int64

In [5]:

    

train.Item_Weight = train.Item_Weight.fillna(np.nanmedian(train.Item_Weight))
test.Item_Weight = test.Item_Weight.fillna(np.nanmedian(test.Item_Weight))


    

In [6]:

    

print train.Outlet_Size.unique()
print test.Outlet_Size.unique()


    

    




['Medium' nan 'High' 'Small']
['Medium' nan 'Small' 'High']

In [7]:

    

train.Outlet_Size = train.Outlet_Size.fillna(train.Outlet_Size.mode().iloc[0])
test.Outlet_Size = test.Outlet_Size.fillna(train.Outlet_Size.mode().iloc[0])


    

In [8]:

    

print train.isnull().sum()
print test.isnull().sum()


    

    




Item_Identifier              0
Item_Weight                  0
Item_Fat_Content             0
Item_Visibility              0
Item_Type                    0
Item_MRP                     0
Outlet_Identifier            0
Outlet_Establishment_Year    0
Outlet_Size                  0
Outlet_Location_Type         0
Outlet_Type                  0
Item_Outlet_Sales            0
dtype: int64
Item_Identifier              0
Item_Weight                  0
Item_Fat_Content             0
Item_Visibility              0
Item_Type                    0
Item_MRP                     0
Outlet_Identifier            0
Outlet_Establishment_Year    0
Outlet_Size                  0
Outlet_Location_Type         0
Outlet_Type                  0
dtype: int64

In [9]:

    

print train.Item_Fat_Content.unique()
print test.Item_Fat_Content.unique()
print train.Item_Type.unique()
print test.Item_Type.unique()
print train.Outlet_Identifier.unique()
print test.Outlet_Identifier.unique()
print train.Outlet_Size.unique()
print test.Outlet_Size.unique()
print train.Outlet_Location_Type.unique()
print test.Outlet_Location_Type.unique()
print train.Outlet_Type.unique()
print test.Outlet_Type.unique()


    

    




['Low Fat' 'Regular' 'low fat' 'LF' 'reg']
['Low Fat' 'reg' 'Regular' 'LF' 'low fat']
['Dairy' 'Soft Drinks' 'Meat' 'Fruits and Vegetables' 'Household'
 'Baking Goods' 'Snack Foods' 'Frozen Foods' 'Breakfast'
 'Health and Hygiene' 'Hard Drinks' 'Canned' 'Breads' 'Starchy Foods'
 'Others' 'Seafood']
['Snack Foods' 'Dairy' 'Others' 'Fruits and Vegetables' 'Baking Goods'
 'Health and Hygiene' 'Breads' 'Hard Drinks' 'Seafood' 'Soft Drinks'
 'Household' 'Frozen Foods' 'Meat' 'Canned' 'Starchy Foods' 'Breakfast']
['OUT049' 'OUT018' 'OUT010' 'OUT013' 'OUT027' 'OUT045' 'OUT017' 'OUT046'
 'OUT035' 'OUT019']
['OUT049' 'OUT017' 'OUT010' 'OUT027' 'OUT046' 'OUT018' 'OUT045' 'OUT019'
 'OUT013' 'OUT035']
['Medium' 'High' 'Small']
['Medium' 'Small' 'High']
['Tier 1' 'Tier 3' 'Tier 2']
['Tier 1' 'Tier 2' 'Tier 3']
['Supermarket Type1' 'Supermarket Type2' 'Grocery Store'
 'Supermarket Type3']
['Supermarket Type1' 'Grocery Store' 'Supermarket Type3'
 'Supermarket Type2']

In [10]:

    

train.Item_Fat_Content = train.Item_Fat_Content.replace(['low fat', 'LF'], ['Low Fat', 'Low Fat'])
test.Item_Fat_Content = test.Item_Fat_Content.replace(['low fat', 'LF'], ['Low Fat', 'Low Fat'])
train.Item_Fat_Content = train.Item_Fat_Content.replace(['reg'], ['Regular'])
test.Item_Fat_Content = test.Item_Fat_Content.replace(['reg'], ['Regular'])


    

In [11]:

    

print train.Item_Fat_Content.unique()
print test.Item_Fat_Content.unique()


    

    




['Low Fat' 'Regular']
['Low Fat' 'Regular']

In [12]:

    

from sklearn.model_selection import train_test_split

train = train.drop('Item_Identifier',axis=1)
test = test.drop('Item_Identifier',axis=1)

y = train.Item_Outlet_Sales
X = train.drop(['Item_Outlet_Sales'], axis=1)

X_train, X_validation, y_train, y_validation = train_test_split(X, y, train_size=0.7, test_size=0.3, random_state=410)


    

In [16]:

    

from catboost import CatBoostRegressor
%matplotlib inline

# indicate categorical features for CatBoost
categorical_features_indices = np.where(X.dtypes != np.float)[0]

model=CatBoostRegressor(iterations=50, depth=3, learning_rate=0.1, loss_function='RMSE',
                       train_dir='model_1/',   # define output folder
                        name='model_depth_1')
model.fit(X_train, y_train, cat_features=categorical_features_indices,
          use_best_model=True,
          eval_set=(X_validation, y_validation), plot=True)


    

    






            
            
        






    
Out[16]:





<catboost.core._CatBoostBase at 0x112607650>






    






 
 

In [ ]:

    

# Took me a while to figure out how to generate the above plot, you can find details here:
## https://stackoverflow.com/questions/45707010/ipython-importerror-cannot-import-name-layout


    

In [18]:

    

# You can also save pre-trained model and load the model later

model.save_model('catboost_model.dump')

model = CatBoostRegressor()
model.load_model('catboost_model.dump')


    

    
Out[18]:





<catboost.core._CatBoostBase at 0x112b50a50>