# -*- coding: utf-8 -*-
"""
Created on Mon Apr 15 13:39:19 2019

@author: GoodManMcGee
"""

import pandas as pd
from sklearn.metrics import accuracy_score
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn.metrics import confusion_matrix
from sklearn.ensemble import RandomForestClassifier
from IPython.display import Image
from sklearn.tree import export_graphviz
from treeinterpreter import treeinterpreter as ti
import matplotlib.pyplot as plt
import numpy as np
import itertools

data = pd.read_csv("pancreatic_cancer_smokers.csv")
target = data['case (1: case, 0: control)']
data.drop('case (1: case, 0: control)', axis=1, inplace=True)
x_train, x_test, y_train, y_test = train_test_split(data, target, test_size = 0.2)
clf = RandomForestClassifier(n_estimators=100)
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
clf_accuracy = accuracy_score(y_test, y_pred)
clf_pred, clf_bias, contributions = ti.predict(clf, x_test)


#The code below was taken from DataDive's treeinterpreter tutorial.
#The aforementioned messages applies to all code between the underscores
#///////////////////////////////////////////

for i in range(len(x_test)):
    print ("Instance", i)
    print ("Bias (trainset mean)", clf_bias[i])
    print ("Feature contributions:")
    for c, feature in sorted(zip(contributions[i], data.feature_names),
                             key=lambda x: -abs(x[0])):
#An error occurs in the "data.feature_names" method in the code above:AttributeError: 'DataFrame' object has no attribute 'feature_names'. I have tried referenceing columns from datasets also, but that also leads to errors: ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
        print (feature, round(c, 2))
    print ("-"*20)
#///////////////////////////////////////////