Download Optimizing KNN Classifier: Finding Best Neighbors & Visualizing Misclassification and more Thesis Information Technology in PDF only on Docsity!
import pandas as pd
define column names
names = ['ax','ay', 'az', 'gx', 'gy', 'gz', 'anglex', 'angley', 'anglez', 'class'] df = pd.read_csv('C:/Users/AMCS2/Desktop/ML-PAPER/A9-SFU-SFB-SFR-SFL-S-SOC-R-WS-F-MT5-8-9- 11000R.csv', header=None, names=names) df.head() import numpy as np from sklearn.model_selection import train_test_split
create design matrix X and target vector y
X = np.array(df.iloc[:, 1:9]) # end index is exclusive y = np.array(df['class']) # another way of indexing a pandas df
split into train and test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=42) from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import accuracy_score
creating odd list of K for KNN
neighbors = list(range(1, 55, 2))
empty list that will hold cv scores
cv_scores = [] from sklearn.model_selection import cross_val_score
perform 10-fold cross validation
for k in neighbors: knn = KNeighborsClassifier(n_neighbors=k) scores = cross_val_score(knn, X_train, y_train, cv=10, scoring='accuracy') cv_scores.append(scores.mean())
changing to misclassification error
mse = [1 - x for x in cv_scores]
determining best k
optimal_k = neighbors[mse.index(min(mse))] print("The optimal number of neighbors is {}".format(optimal_k))
plot misclassification error vs k
import matplotlib.pyplot as plt plt.dpi= plt.rcParams["figure.figsize"] = (10,5) plt.plot(neighbors, mse) plt.xlabel("Number of Neighbors K") plt.ylabel("Misclassification Error")
plt.tick_params(colors='black',labelsize=12,bottom=2,width=2,length=2) # ปปปปปปปปปปปปปป
plt.grid(True) plt.show()
instantiate learning model (k = 5)
