#Kevin Tran
#3-21-18
#Problem 1 sklearn svm and class

import numpy as np
from sklearn import preprocessing, cross_validation, neighbors, svm
import pandas as pd
import random
from svm import Support_Vector_Machine
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix


df = pd.read_csv('cancer.txt')
df.replace('?', -99999, inplace=True)
df.drop(df.columns[0], 1, inplace=True)

df.drop(df.columns[[1,2,4,5,6,7,8]], axis=1, inplace=True)
X = np.array(df.drop([df.columns[2]], 1))
y = np.array(df[df.columns[2]])
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.4)

clf = svm.SVC()
clf.fit(X_train, y_train)
confidence = clf.score(X_test, y_test)

print("Predicted Table of X_Test:")
print(clf.predict(X_test), "\n")
print("SKLEARN confidence score: ", confidence, "\n")
print("Begin in class SVM\n")

pred = clf.predict(X_test)
print(confusion_matrix(y_test, pred))
print(classification_report(y_test, pred))

#
# Email said to use example as the test
#

df = pd.read_csv("cancer.txt")
df.replace('?',-99999, inplace=True)
df.drop(df.columns[0], 1, inplace=True)

full_data = df.astype(float).values.tolist()
random.shuffle(full_data)
#test_data = df['ct','bn']

test_size = 0.4
train_set = {2:[], 4:[]}
test_set = {2:[], 4:[]}
train_data = full_data[:-int(test_size*len(full_data))]
test_data = full_data[-int(test_size*len(full_data)):]

data_dict = train_set
for i in train_data:
    train_set[i[-1]].append(i[:-1])

for i in test_data:
    test_set[i[-1]].append(i[:-1])

svm = Support_Vector_Machine()
svm.fit(data=data_dict)

predict_us = [[0,10],
              [1,3],
              [3,4],
              [3,5],
              [5,5],
              [5,6],
              [6,-5],
              [5,8]]

for p in test_set:
    svm.predict(p)