#!/usr/bin/env python
# coding: utf-8
# # Example of usage model from sklift.models in sklearn.pipeline
#
#
#
#
#
#
#
# SCIKIT-UPLIFT REPO |
# SCIKIT-UPLIFT DOCS
#
# RUSSIAN VERSION
#
#
# This is a simple example on how to use [sklift.models](https://scikit-uplift.readthedocs.io/en/latest/api/models.html) with [sklearn.pipeline](https://scikit-learn.org/stable/modules/classes.html#module-sklearn.pipeline).
#
# The data is taken from [MineThatData E-Mail Analytics And Data Mining Challenge dataset by Kevin Hillstrom](https://blog.minethatdata.com/2008/03/minethatdata-e-mail-analytics-and-data.html).
#
# This dataset contains 64,000 customers who last purchased within twelve months. The customers were involved in an e-mail test:
# * 1/3 were randomly chosen to receive an e-mail campaign featuring Mens merchandise.
# * 1/3 were randomly chosen to receive an e-mail campaign featuring Womens merchandise.
# * 1/3 were randomly chosen to not receive an e-mail campaign.
#
# During a period of two weeks following the e-mail campaign, results were tracked. The task is to tell the world if the Mens or Womens e-mail campaign was successful.
#
# The full description of the dataset can be found at the [link](https://blog.minethatdata.com/2008/03/minethatdata-e-mail-analytics-and-data.html).
#
# Firstly, install the necessary libraries:
# In[1]:
get_ipython().system('pip install scikit-uplift==0.1.1 xgboost==1.0.2 category_encoders==2.1.0')
# Secondly, load the data:
# In[2]:
import urllib.request
import pandas as pd
csv_path = '/content/Hilstorm.csv'
url = 'http://www.minethatdata.com/Kevin_Hillstrom_MineThatData_E-MailAnalytics_DataMiningChallenge_2008.03.20.csv'
urllib.request.urlretrieve(url, csv_path)
# For simplicity of the example, we will leave only two user segments:
# * those who were sent an e-mail advertising campaign with women's products;
# * those who were not sent out the ad campaign.
#
# We will use the `visit` variable as the target variable.
# In[3]:
import pandas as pd
get_ipython().run_line_magic('matplotlib', 'inline')
dataset = pd.read_csv(csv_path)
print(f'Shape of the dataset before processing: {dataset.shape}')
dataset = dataset[dataset['segment']!='Mens E-Mail']
dataset.loc[:, 'treatment'] = dataset['segment'].map({
'Womens E-Mail': 1,
'No E-Mail': 0
})
dataset = dataset.drop(['segment', 'conversion', 'spend'], axis=1)
print(f'Shape of the dataset after processing: {dataset.shape}')
dataset.head()
# Divide all the data into a training and validation sample:
# In[4]:
from sklearn.model_selection import train_test_split
Xyt_tr, Xyt_val = train_test_split(dataset, test_size=0.5, random_state=42)
X_tr = Xyt_tr.drop(['visit', 'treatment'], axis=1)
y_tr = Xyt_tr['visit']
treat_tr = Xyt_tr['treatment']
X_val = Xyt_val.drop(['visit', 'treatment'], axis=1)
y_val = Xyt_val['visit']
treat_val = Xyt_val['treatment']
# Select categorical features:
# In[5]:
cat_cols = X_tr.select_dtypes(include='object').columns.tolist()
print(cat_cols)
# Create the necessary objects and combining them into a pipieline:
# In[6]:
from sklearn.pipeline import Pipeline
from category_encoders import CatBoostEncoder
from sklift.models import ClassTransformation
from xgboost import XGBClassifier
encoder = CatBoostEncoder(cols=cat_cols)
estimator = XGBClassifier(max_depth=2, random_state=42)
ct = ClassTransformation(estimator=estimator)
my_pipeline = Pipeline([
('encoder', encoder),
('model', ct)
])
# Train pipeline as usual, but adding the treatment column in the step model as a parameter `model__treatment`.
# In[7]:
my_pipeline = my_pipeline.fit(
X=X_tr,
y=y_tr,
model__treatment=treat_tr
)
# Predict the uplift and calculate the uplift@30%
# In[8]:
from sklift.metrics import uplift_at_k
uplift_predictions = my_pipeline.predict(X_val)
uplift_30 = uplift_at_k(y_val, uplift_predictions, treat_val, strategy='overall')
print(f'uplift@30%: {uplift_30:.4f}')