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

# In[1]:


from sklearn.datasets import load_breast_cancer
bc = load_breast_cancer()


# In[2]:


import pandas as pd
bc_df = pd.DataFrame(bc.data, columns=bc.feature_names)
bc_df.head()


# In[3]:


from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(bc_df, bc.target, test_size = 0.2, random_state = 31)
print(X_train.shape)
print(Y_train.shape)
print(X_test.shape)
print(Y_test.shape)


# In[4]:


from aix360.algorithms.rbm import FeatureBinarizer
fb = FeatureBinarizer(negations=True)
X_train_fb = fb.fit_transform(X_train)
X_test_fb = fb.transform(X_test)
X_train_fb['mean radius'][:8]


# In[5]:


from aix360.algorithms.rbm import GLRMExplainer, LogisticRuleRegression


# In[6]:


logistic_model = LogisticRuleRegression(maxSolverIter=2000)
explainer = GLRMExplainer(logistic_model)
explainer.fit(X_train_fb, Y_train)


# In[7]:


Y_pred = explainer.predict(X_test_fb)


# In[8]:


from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
print(f'Accuracy = {accuracy_score(Y_test, Y_pred)}')
print(f'Precision = {precision_score(Y_test, Y_pred, average="macro")}')
print(f'Recall = {recall_score(Y_test, Y_pred, average="macro")}')
print(f'F1 = {f1_score(Y_test, Y_pred, average="macro")}')


# In[9]:


explainer.explain()


# In[10]:


get_ipython().run_line_magic('matplotlib', 'inline')

fb = FeatureBinarizer(negations=True)
figs, _ = explainer.visualize(bc_df, fb)


# In[ ]: