import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn import preprocessing
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn import svm
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import StratifiedShuffleSplit

data=pd.read_csv("./kaggle/data.csv")
data=data.drop('Unnamed: 32',axis=1)
data=data.fillna(data.mean())

X=np.array(data.drop('diagnosis',axis=1))
Y=np.array(data['diagnosis'])
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.25, random_state=42)


def svc_param_selection(X, y, nfolds,X_test,y_test):
	C_range = np.logspace(-2, 10, 13)
	gamma_range = np.logspace(-9, 3, 13)
	param_grid = dict(gamma=gamma_range, C=C_range)

	grid_search = GridSearchCV(svm.SVC(), param_grid, cv=nfolds)
	grid_search.fit(X, y)
	predicted=grid_search.predict(X_test)
	score=accuracy_score(y_test, predicted)
	return grid_search.best_params_


cv = StratifiedShuffleSplit(n_splits=5, test_size=0.2, random_state=42)
param=svc_param_selection(X_train,y_train,cv,X_test,y_test)
print param