dowhy使用demo

#encoding=utf-8
import pandas as pd
import numpy as np
from dowhy import CausalModel
data= pd.read_csv("https://raw.githubusercontent.com/AMLab-Amsterdam/CEVAE/master/datasets/IHDP/csv/ihdp_npci_1.csv", header = None)#加载数据
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()
print(data)
# 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',#这个因素是主要因素能看出来的
        outcome='y_factual',#这个是结果
        common_causes=xs.split('+')
        )
#Identify the causal effect
identified_estimand = model.identify_effect()#识别过程
# 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
)#评估过程

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"]))

refute_results=model.refute_estimate(identified_estimand, estimate,
        method_name="random_common_cause")#反驳过程
print(refute_results)