NameError: name 'train_predict' is not defined

[asifrpa]

from sklearn.neighbors import KNeighborsClassifier
X_train_cv, X_test_cv, y_train_cv, y_test_cv = train_test_split(X_train, y_train, test_size = 0.3, random_state=100)
neighbors = []
accuracy = []
for n in range(3,10):
knn = KNeighborsClassifier(n_neighbors=n)
print("Number of neighbors is: {}".format(n))
train_predict(knn, X_train_cv, y_train_cv, X_test_cv, y_test_cv)
clf_ = knn.fit(X_train, y_train)
y_pred = clf_.predict(X_test)
neighbors.append(n)
accuracy.append( str(("%.2f" %(accuracy_score(y_test,y_pred)* 100) )))
accuracy.sort()
neighbors.sort()
plt.bar( list(range(3, 10)), accuracy, tick_label=neighbors, width=0.8, color="rgbymc")
plt.title("Optimizing Neighbours for KNN")
plt.xlabel("Neighbours")
plt.ylabel("accuracy")
plt.ylim(0)
plt.show()

ERROR
NameError Traceback (most recent call last)
in
6 knn = KNeighborsClassifier(n_neighbors=n)
7 print("Number of neighbors is: {}".format(n))
----> 8 train_predict(knn, X_train_cv, y_train_cv, X_test_cv, y_test_cv)
9 clf_ = knn.fit(X_train, y_train)
10 y_pred = clf_.predict(X_test)

NameError: name 'train_predict' is not defined

[JonnoFTW]

Have you defined or imported the function anywhere in your code?

[asifrpa]

def train_predict(clf, X_train, y_train, X_test, y_test):

Defined like this....later in the code

Not imported anywhere else in the code

[asifrpa]

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_predict
X_train_cv, X_test_cv, y_train_cv, y_test_cv = train_test_split(X_train, y_train, test_size = 0.3, random_state=100)
neighbors = []
accuracy = []
for n in range(3,10):
knn = KNeighborsClassifier(n_neighbors=n)
print("Number of neighbors is: {}".format(n))
train_predict(knn, X_train_cv, y_train_cv, X_test_cv, y_test_cv)
clf_ = knn.fit(X_train, y_train)
y_pred = clf_.predict(X_test)
neighbors.append(n)
accuracy.append( str(("%.2f" %(accuracy_score(y_test,y_pred)* 100) )))
accuracy.sort()
neighbors.sort()
plt.bar( list(range(3, 10)), accuracy, tick_label=neighbors, width=0.8, color="rgbymc")
plt.title("Optimizing Neighbours for KNN")
plt.xlabel("Neighbours")
plt.ylabel("accuracy")
plt.ylim(0)
plt.show()

ImportError Traceback (most recent call last)
in
1 from sklearn.neighbors import KNeighborsClassifier
----> 2 from sklearn.model_selection import train_predict
3 X_train_cv, X_test_cv, y_train_cv, y_test_cv = train_test_split(X_train, y_train, test_size = 0.3, random_state=100)
4 neighbors = []
5 accuracy = []

ImportError: cannot import name 'train_predict' from 'sklearn.model_selection' (C:\Users\MyPc\Anaconda3\lib\site-packages\sklearn\model_selection_init_.py)

[asifrpa]

def train_clf(clf, X_train, y_train):

 return clf.fit(X_train, y_train)

def pred_clf(clf, features, target):

y_pred = clf.predict(features)
return f1_score(target.values, y_pred, pos_label = 1)

def train_predict(clf, X_train, y_train, X_test, y_test):

train_clf(clf, X_train, y_train)

print("F1 score for training set is: {:.4f}".format(pred_clf(clf, X_train, y_train)))
print("F1 score for testing set is: {:.4f}\n".format(pred_clf(clf, X_test, y_test)))

[JonnoFTW]

If your methods are so short, consider just putting them inside your main function that you want to optimise.

Additionally, no such function train_predict exists inside sklearn.model_selection. Also consider formatting your code so it's easier to read. Place the code between a pair of ```