SVM

import numpy as np # linear algebra

import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn.model_selection import train_test_split

data = pd.read_csv("/home/umesh/Desktop/icfoss/bcdata.csv")

data.info()

data.drop(['Unnamed: 32'], axis=1, inplace=True)

data.head()

data.drop(['id'], axis=1, inplace=True)

data.diagnosis.value_counts()

data.diagnosis = [1 if each == "M" else 0 for each in data.diagnosis]

y = data.diagnosis.values

x = data.drop(['diagnosis'], axis=1)

x = (x - np.min(x) ) / ( np.max(x) - np.min(x) ).values

f, axis = plt.subplots(figsize = (18,18))

sns.heatmap(data.corr(), annot = False, linewidths = .4)

plt.show()

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.3 , random_state = 1)

print x_train

print x_test

print y_train

print y_test

# svm

from sklearn.svm import SVC

svm = SVC(random_state = 1)

svm.fit(x_train,y_train)

print("accuracy of svm algo:",svm.score(x_test,y_test))

# confusion matrix

y_pred = svm.predict(x_test)

y_true = y_test

from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_true,y_pred)

print cm

import seaborn as sns

sns.heatmap(cm, annot = True, linewidths = 0.5 , linecolor = "yellow", fmt =".0f")

plt.xlabel("y_true")

plt.ylabel("y_pred")

plt.show()