KNN.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

df = pd.read_csv('/Data/Classified Data', index_col=0)

# scale features to similar size so features with large numbers aren't weighted more heavily
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])

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(df_feat, df['TARGET CLASS'], test_size=0.3, random_state=101)

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors = 18)
knn.fit(X_train, y_train)

predictions = knn.predict(X_test)
from sklearn.metrics import confusion_matrix, classification_report

print(confusion_matrix(y_test, predictions))
print(classification_report(y_test, predictions))

error_rate=[]
for i in range(1, 40):
    knn = KNeighborsClassifier(n_neighbors = i)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)
    error_rate.append(np.mean(predictions != y_test))

#plt.plot(range(1, 40), error_rate, marker='o', markerfacecolor='red')
plt.show()