Community

SVM using scikit

[CODE]
import pandas as pd
import numpy as np
from sklearn import svm, preprocessing
FEATURES = ['WAGE'']
def Build_Data_Set():
df = pd.read_csv("IT_new1.csv")
df = df.reindex(np.random.permutation(df.index))
df = df.replace("NaN",0).replace("N/A",0)
X = np.array(df[FEATURES].values)
y = df['Outcome'].values.tolist()
        X = preprocessing.scale(X)
return X,y


def Analysis():
test_size = 1000
X,y = Build_Data_Set()
print(len(X))
clf = svm.SVC(kernel="linear", C= 1.0)
clf.fit(X[:-test_size],y[:-test_size])

correct_count = 0
for x in range(1,test_size + 1):
if clf.predict(X[-x])[0] == y[-x]:
correct_count += 1

print("Accuracy:", (correct_count/test_size) * 100)


Build_Data_Set()
Analysis()
[/CODE]


Explanation : Wage is numerical column
ERROR: C:UsersHPAnaconda2libsite-packagessklearnutilsvalidation.py:395: DeprecationWarning: Passing 1d arrays as data is deprecated in 0.17 and will raise ValueError in 0.19. Reshape your data either using X.reshape(-1, 1) if your data has a single feature or X.reshape(1, -1) if it contains a single sample.
  DeprecationWarning)

Please tell me how to get rid of this error