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

# In[1]:


from dowhy import CausalModel
import dowhy.datasets
import numpy as np
import pandas as pd

import warnings
warnings.filterwarnings('ignore')

import logging
#logging.getLogger("dowhy").setLevel(logging.INFO)
np.random.seed(25)
dowhy.__version__


# In[2]:


data = dowhy.datasets.linear_dataset(10, num_common_causes=2, num_samples=100000,
                                     num_instruments=0, num_effect_modifiers=2,
                                     num_treatments=1,
                                     treatment_is_binary=True,
                                    outcome_is_binary=False)
df = data['df']
print(df.head())
print(data)


# In[3]:


model = CausalModel(df,
                    data["treatment_name"],data["outcome_name"],
                    data["dot_graph"],
                   missing_nodes_as_confounders=True,
                   logging_level=logging.INFO)

print("CC", model._common_causes)
print("EM", model._effect_modifiers)
model.view_model()
from IPython.display import Image, display
display(Image(filename="causal_model.png"))


# In[4]:


logging.getLogger("causal_estimar")


# In[5]:


identified_estimand = model.identify_effect(proceed_when_unidentifiable=True)
import time
start=time.time()
causal_estimate = model.estimate_effect(identified_estimand,
                                        method_name="backdoor.linear_regression",
                                       confidence_intervals=False,
                                       test_significance=False,
                                        method_params = {
                                            'num_null_simulations':10,
                                            'num_simulations':10,
                                            'num_quantiles_to_discretize_cont_cols':10,
                                            'fit_method': "statsmodels",
                                            'need_conditional_estimates':False
                                        },
                                       )
end=time.time()
print(end-start)
#print(causal_estimate.estimator._linear_model.summary())
#print(causal_estimate)


# In[6]:


causal_estimate.test_stat_significance(num_simulations=2)


# In[ ]:


print(causal_estimate.estimate_conditional_effects(effect_modifiers=["X1" ]).head(20))


# In[ ]:


from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LassoCV
from sklearn.ensemble import GradientBoostingRegressor
dml_estimate = model.estimate_effect(identified_estimand, method_name="backdoor.econml.dml.DMLCateEstimator",
                                     control_value = 0,
                                     treatment_value = 1,
                                 target_units = "ate",  # condition used for CATE
                                 confidence_intervals=False,
                                method_params={"init_params":{'model_y':GradientBoostingRegressor(),
                                                              'model_t': GradientBoostingRegressor(),
                                                              "model_final":LassoCV(), 
                                                              'featurizer':PolynomialFeatures(degree=1, include_bias=True)},
                                               "fit_params":{}})
print(dml_estimate)


# In[ ]:


print(causal_estimate.test_stat_significance(method="bootstrap", num_null_simulations=2))
print(causal_estimate.test_stat_significance())
causal_estimate.test_stat_significance()


# In[ ]:


print(causal_estimate.get_standard_error(method="bootstrap", num_ci_simulations=10, sample_size_fraction=0.9))


# In[ ]:


print(causal_estimate.get_confidence_intervals(confidence_level=0.99))
print(causal_estimate.get_confidence_intervals(method="bootstrap", confidence_level=0.95, num_ci_simulations=10))
print(causal_estimate.get_confidence_intervals(method="psm", confidence_level=0.95, num_ci_simulations=10))


# In[15]:


str(model.refute_estimate(identified_estimand, causal_estimate, method_name="placebo_treatment_refuter", num_simulations=1))


# In[ ]:


import statsmodels.formula.api as smf
res=smf.ols(formula="y~v0+W0+W1+W2+W3", data=df).fit()
res.summary()


# In[ ]:


lm = causal_estimate.estimator._linear_model
print(lm.pvalues)
print(type(lm.conf_int()))
print(lm.bse)
lm.summary()


# In[ ]:


print(causal_estimate.get_confidence_intervals(confidence_level =0.9))


# In[ ]:


print(causal_estimate.get_standard_error())


# In[ ]:


print(causal_estimate.test_stat_significance())


# In[ ]: