By Scikit Learn:
import numpy as np
from sklearn import preprocessing, cross_validation, neighbors
import pandas as pd
df = pd.read_csv('breast-cancer-wisconsin.data.txt')
df.replace('?',-99999, inplace=True)
df.drop(['id'], 1, inplace=True)
X = np.array(df.drop(['class'], 1))
y = np.array(df['class'])
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.2)
clf = neighbors.KNeighborsClassifier()
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)
print(accuracy)
Build your own model:
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
import warnings
from collections import Counter
#dont forget this
import pandas as pd
import random
style.use('fivethirtyeight')
def k_nearest_neighbors(data, predict, k=3):
if len(data) >= k:
warnings.warn('K is set to a value less than total voting groups!')
distances = []
for group in data:
for features in data[group]:
euclidean_distance = np.linalg.norm(np.array(features)-np.array(predict))
distances.append([euclidean_distance,group])
votes = [i[1] for i in sorted(distances)[:k]]
vote_result = Counter(votes).most_common(1)[0][0]
return vote_result
df = pd.read_csv('breast-cancer-wisconsin.data.txt')
df.replace('?',-99999, inplace=True)
df.drop(['id'], 1, inplace=True)
full_data = df.astype(float).values.tolist()
random.shuffle(full_data)
test_size = 0.2
train_set = {2:[], 4:[]}
test_set = {2:[], 4:[]}
train_data = full_data[:-int(test_size*len(full_data))]
test_data = full_data[-int(test_size*len(full_data)):]
for i in train_data:
train_set[i[-1]].append(i[:-1])
for i in test_data:
test_set[i[-1]].append(i[:-1])
correct = 0
total = 0
for group in test_set:
for data in test_set[group]:
vote = k_nearest_neighbors(train_set, data, k=5)
if group == vote:
correct += 1
total += 1
print('Accuracy:', correct/total)
Point to be know before you consider:
1. Whats your data volume (should not be in TB)
2. What should be value of "K" (depending upon your requirement, having high K value doesn't mean you will get better accuracy, in-fact opposite is what I observed)
3. Can you multithread your algorithm ? (Scikit KNN algorithm is already multithreaded (n_jobs = -1))
4. Difference between Accuracy and Confidence
5. Do you need to define Radius ?
