machinelearningclassification/module3.py at master · codehard123/machinelearningclassification · GitHub

25 lines (22 loc) · 673 Bytes

import csv

import numpy

import scipy

import matplotlib.pyplot as plt

from sklearn import preprocessing

from sklearn.cross_validation import train_test_split

from sklearn import metrics

#Imports for Module 4

from sklearn import neighbors

import knnplots

#Code common to all modeles from module 3 onwards

##NB. The X and yTransformed variables come from the preprocessing in the previous module.

fileName = "wdbc.csv"

fileOpen = open(fileName, "rU")

csvData = csv.reader(fileOpen)

dataList = list(csvData)

dataArray = numpy.array(dataList)

X = dataArray[:,2:32].astype(float)

y = dataArray[:, 1]

le = preprocessing.LabelEncoder()

le.fit(y)

yTransformed = le.transform(y)

Expand file tree