import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
dataFileName='RandomForestInput.xlsx'
sheetName='Data'
dataRaw=pd.read_excel(dataFileName,sheetname=sheetName)
noData=len(dataRaw)
import matplotlib.pylab as plt
from sklearn.cross_validation import train_test_split
from sklearn.cross_validation import cross_val_score
from sklearn.preprocessing import StandardScaler
import pandas as pd
import numpy as np

labels=['x1','x2','x3']
x=dataRaw[labels]
y=dataRaw['y']

X_train,X_test,Y_train,Y_test=train_test_split(x,y,test_size=0.1,random_state=0)

sc=StandardScaler()
sc.fit(X_train)
x_std=sc.transform(x)
X_train_std=sc.transform(X_train)
X_test_std=sc.transform(X_test)

from sklearn.svm import SVC
from numpy import stack
from sklearn.metrics import accuracy_score
from sklearn.svm import SVR

linear_svm=SVC(kernel='linear')
linear_svm.fit(X_train_std,Y_train)
y_pred=linear_svm.predict(X_test_std)
coef=linear_svm.coef_[0]
coef=np.absolute(coef)
svm_indices=np.argsort(coef)[::-1]
print('Linear SVM')
print("Accuracy: %.2f" %accuracy_score(Y_test,y_pred))
for f in range(X_train.shape[1]):
    print(("%2d) %-*s %f" % (f+1,30,labels[svm_indices[f]],coef[svm_indices[f]])))

from sklearn.ensemble import RandomForestClassifier
from numpy import stack
from sklearn.metrics import accuracy_score
forest=RandomForestClassifier(criterion='entropy',n_estimators=100,random_state=1,n_jobs=2)
forest.fit(X_train,Y_train)
y_pred=forest.predict(X_test)
#forest.fit=(X_train,Y_train)
#y_pred=forest.predict(X_test)
importances=forest.feature_importances_
indices=np.argsort(importances)[::-1]
print('RandonForest')
print("Accuracy: %.2f" % accuracy_score(Y_test,y_pred))
for f in range(X_train.shape[1]):
    print(("%2d) %-*s %f" %(f+1,30,labels[indices[f]],importances[indices[f]])))