#!/usr/bin/env python
# coding: utf-8

# # DoWhy example on ihdp (Infant Health and Development Program) dataset

# In[1]:


# importing required libraries
import os, sys
sys.path.append(os.path.abspath("../../../"))
import dowhy
from dowhy import CausalModel
import pandas as pd
import numpy as np


# ### Loading Data

# In[2]:


data= pd.read_csv("https://raw.githubusercontent.com/AMLab-Amsterdam/CEVAE/master/datasets/IHDP/csv/ihdp_npci_1.csv", header = None)
col =  ["treatment", "y_factual", "y_cfactual", "mu0", "mu1" ,]
for i in range(1,26):
    col.append("x"+str(i))
data.columns = col
data = data.astype({"treatment":'bool'}, copy=False)
data.head()


# ### 1.Model

# In[3]:


# Create a causal model from the data and given common causes.
xs = ""
for i in range(1,26):
    xs += ("x"+str(i)+"+")
    
model=CausalModel(
        data = data,
        treatment='treatment',
        outcome='y_factual',
        common_causes=xs.split('+')
        )


# ### 2.Identify

# In[4]:


#Identify the causal effect
identified_estimand = model.identify_effect()


# ### 3. Estimate (using different methods)

# #### 3.1 Using Linear Regression

# In[5]:


# Estimate the causal effect and compare it with Average Treatment Effect
estimate = model.estimate_effect(identified_estimand,
        method_name="backdoor.linear_regression", test_significance=True
)

print(estimate)

print("Causal Estimate is " + str(estimate.value))
data_1 = data[data["treatment"]==1]
data_0 = data[data["treatment"]==0]

print("ATE", np.mean(data_1["y_factual"])- np.mean(data_0["y_factual"]))


# #### 3.2 Using Propensity Score Matching

# In[6]:


estimate = model.estimate_effect(identified_estimand,
        method_name="backdoor.propensity_score_matching"
)

print("Causal Estimate is " + str(estimate.value))

print("ATE", np.mean(data_1["y_factual"])- np.mean(data_0["y_factual"]))


# #### 3.3 Using Propensity Score Stratification

# In[7]:


estimate = model.estimate_effect(identified_estimand,
        method_name="backdoor.propensity_score_stratification", method_params={'num_strata':50, 'clipping_threshold':5}
)

print("Causal Estimate is " + str(estimate.value))
print("ATE", np.mean(data_1["y_factual"])- np.mean(data_0["y_factual"]))



# #### 3.4 Using Propensity Score Weighting

# In[8]:


estimate = model.estimate_effect(identified_estimand,
        method_name="backdoor.propensity_score_weighting"
)

print("Causal Estimate is " + str(estimate.value))

print("ATE", np.mean(data_1["y_factual"])- np.mean(data_0["y_factual"]))


# ### 4. Refute
# ##### Refute the obtained estimate using multiple robustness checks.
# ##### 4.1 Adding a random common cause

# In[9]:


refute_results=model.refute_estimate(identified_estimand, estimate,
        method_name="random_common_cause")
print(refute_results)


# ##### 4.2 Using a placebo treatment

# In[10]:


res_placebo=model.refute_estimate(identified_estimand, estimate,
        method_name="placebo_treatment_refuter", placebo_type="permute")
print(res_placebo)


# #### 4.3 Data Subset Refuter

# In[11]:


res_subset=model.refute_estimate(identified_estimand, estimate,
        method_name="data_subset_refuter", subset_fraction=0.9)
print(res_subset)