sKleran KNN

import pandas as pd
import sklearn.preprocessing as preprocessing
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn import metrics



col_names = ["ID","K1K2驱动信号","电子锁驱动信号","急停信号","门禁信号","THDV-M","THDI-M","label"]
data = pd.read_csv("data_train.csv",names=col_names)
# print(data.info())
# print(data.describe())
dataset_X = data[["K1K2驱动信号","电子锁驱动信号","急停信号","门禁信号","THDV-M","THDI-M"]].as_matrix()
dataset_Y = data[["label"]].as_matrix()
X_train, X_val, y_train, y_val = train_test_split(dataset_X, dataset_Y,
                                                  test_size=0.2,
                                                  random_state=42)


print(dataset_X)
print(dataset_Y)
knn=KNeighborsClassifier(n_neighbors=1)
print("Y_train is :")
print(y_train)
print("ravel is :")
print(y_train.ravel())
print("X_train is :")
print(X_train)
knn.fit(X_train,y_train.ravel())

y_pred_on_train=knn.predict(X_train)
y_pred_on_test=knn.predict(X_val)
print("--------")

acc=metrics.accuracy_score(y_val,y_pred_on_test)
print(acc)

print("+++++++++++++++++++")
print(y_pred_on_test)
print("+++++++++++++++++=")
print(y_val)