scikit-learn utility scripts

ml.py

# train-test split
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test  = train_test_split(X, y, test_size=0.4)

#get accuracy score
print metrics.accuracy_score(y,predict_y)

#get optimum value of k in knn
k_range = range(1,26)
scores = []
for k in k_range:
  knn = KNeighborsClassifier(n_neighbours=k)
  knn.fit(X_train,y_train)
  y_pred = knn.predict(X_test)
  scores.append(metrics.accuracy_score(y_test,y_pred))

plt.plot(k_range,scores)
plt.xlabel('value for k in knn')
plt.ylabel('tesring accuracy')