K Nearest Neighbors with Python (Udemy)

Python-Data-Science-and-Machine-Learning-Bootcamp\Machine Learning Sections\

K Nearest Neighbors with Python

Brief:


parameters
1) K
2) Distance Metric

cons
1) need high volume of data
2) not good with hihg dimensional data
3) Categorcal features don't work well



Steps:

Standardize the Variables

Because the KNN classifier predicts the class of a given test observation by identifying the observations that are nearest to it, the scale of the variables matters. Any variables that are on a large scale will have a much larger effect on the distance between the observations, and hence on the KNN classifier, than variables that are on a small scale.

Code:
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
scaler.fit(df.drop('TARGET CLASS',axis=1))
scaled_features = scaler.transform(df.drop('TARGET CLASS',axis=1))
df_feat = pd.DataFrame(scaled_features,columns=df.columns[:-1])
df_feat.head()

Train Test Split

code

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(scaled_features,df['TARGET CLASS'],

                                                    test_size=0.30)

Using KNN

Remember that we are trying to come up with a model to predict whether someone will TARGET CLASS or not. We'll start with k=1.

code

from sklearn.neighbors import KNeighborsClassifier

knn = KNeighborsClassifier(n_neighbors=1)

knn.fit(X_train,y_train)

pred = knn.predict(X_test)

Predictions and Evaluations

code

from sklearn.metrics import classification_report,confusion_matrix

print(confusion_matrix(y_test,pred))

print(classification_report(y_test,pred))

Choosing a K Value

Let's go ahead and use the elbow method to pick a good K Value:

code

<imp>

error_rate = []

# Will take some time

for i in range(1,40):

    

    knn = KNeighborsClassifier(n_neighbors=i)

    knn.fit(X_train,y_train)

    pred_i = knn.predict(X_test)

    error_rate.append(np.mean(pred_i != y_test))

plt.figure(figsize=(10,6))

plt.plot(range(1,40),error_rate,color='blue', linestyle='dashed', marker='o',

         markerfacecolor='red', markersize=10)

plt.title('Error Rate vs. K Value')

plt.xlabel('K')

plt.ylabel('Error Rate')

code
# FIRST A QUICK COMPARISON TO OUR ORIGINAL K=1
knn = KNeighborsClassifier(n_neighbors=1)

knn.fit(X_train,y_train)
pred = knn.predict(X_test)

print('WITH K=1')
print('\n')
print(confusion_matrix(y_test,pred))
print('\n')
print(classification_report(y_test,pred))



# NOW WITH K=23
knn = KNeighborsClassifier(n_neighbors=23)

knn.fit(X_train,y_train)
pred = knn.predict(X_test)

print('WITH K=23')
print('\n')
print(confusion_matrix(y_test,pred))
print('\n')
print(classification_report(y_test,pred))


outcome

WITH K=23


[[132  11]
 [  5 152]]


             precision    recall  f1-score   support

          0       0.96      0.92      0.94       143
          1       0.93      0.97      0.95       157

avg / total       0.95      0.95      0.95       300