├── README.md
└── breast_cancer_analysis.py


/README.md:
--------------------------------------------------------------------------------
1 | # vishabh
2 | Breast Cancer data analysis
3 | http://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+%28diagnostic%29
4 | 


--------------------------------------------------------------------------------
/breast_cancer_analysis.py:
--------------------------------------------------------------------------------
  1 | # -*- coding: utf-8 -*-
  2 | """
  3 | Created on Wed Aug 29 01:04:23 2018
  4 | 
  5 | @author: 1022316
  6 | """
  7 | 
  8 | #Classification of cancer dignosis
  9 | #importing the libraries
 10 | import numpy as np
 11 | import matplotlib.pyplot as plt
 12 | import pandas as pd
 13 | 
 14 | #importing the dataset 
 15 | dataset = pd.read_csv('C:\Machine learning\cancer_data\cancer.csv')
 16 | X = dataset.iloc[:, 1:31].values
 17 | Y = dataset.iloc[:, 31].values
 18 | 
 19 | dataset.head()
 20 | 
 21 | print("Cancer data set dimensions : {}".format(dataset.shape))
 22 | 
 23 | dataset.groupby('diagnosis').size()
 24 | 
 25 | #Visualization of data
 26 | dataset.groupby('diagnosis').hist(figsize=(12, 12))
 27 | 
 28 | dataset.isnull().sum()
 29 | dataset.isna().sum()
 30 | 
 31 | dataframe = pd.DataFrame(Y)
 32 | #Encoding categorical data values 
 33 | from sklearn.preprocessing import LabelEncoder
 34 | labelencoder_Y = LabelEncoder()
 35 | Y = labelencoder_Y.fit_transform(Y)
 36 | 
 37 | 
 38 | # Splitting the dataset into the Training set and Test set
 39 | from sklearn.model_selection import train_test_split
 40 | X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.25, random_state = 0)
 41 | 
 42 | 
 43 | #Feature Scaling
 44 | from sklearn.preprocessing import StandardScaler
 45 | sc = StandardScaler()
 46 | X_train = sc.fit_transform(X_train)
 47 | X_test = sc.transform(X_test)
 48 | 
 49 | #Fitting the Logistic Regression Algorithm to the Training Set
 50 | from sklearn.linear_model import LogisticRegression
 51 | classifier = LogisticRegression(random_state = 0)
 52 | classifier.fit(X_train, Y_train)
 53 | #95.8 Acuracy
 54 | 
 55 | #Fitting K-NN Algorithm
 56 | from sklearn.neighbors import KNeighborsClassifier
 57 | classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
 58 | classifier.fit(X_train, Y_train)
 59 | #95.1 Acuracy
 60 | 
 61 | #Fitting SVM
 62 | from sklearn.svm import SVC
 63 | classifier = SVC(kernel = 'linear', random_state = 0)
 64 | classifier.fit(X_train, Y_train) 
 65 | #97.2 Acuracy
 66 | 
 67 | #Fitting K-SVM
 68 | from sklearn.svm import SVC
 69 | classifier = SVC(kernel = 'rbf', random_state = 0)
 70 | classifier.fit(X_train, Y_train)
 71 | #96.5 Acuracy
 72 | 
 73 | #Fitting Naive_Bayes
 74 | from sklearn.naive_bayes import GaussianNB
 75 | classifier = GaussianNB()
 76 | classifier.fit(X_train, Y_train)
 77 | #91.6 Acuracy
 78 | 
 79 | #Fitting Decision Tree Algorithm
 80 | from sklearn.tree import DecisionTreeClassifier
 81 | classifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)
 82 | classifier.fit(X_train, Y_train)
 83 | #95.8 Acuracy
 84 | 
 85 | #Fitting Random Forest Classification Algorithm
 86 | from sklearn.ensemble import RandomForestClassifier
 87 | classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
 88 | classifier.fit(X_train, Y_train)
 89 | #98.6 Acuracy
 90 | 
 91 | #predicting the Test set results
 92 | Y_pred = classifier.predict(X_test)
 93 | 
 94 | #Creating the confusion Matrix
 95 | from sklearn.metrics import confusion_matrix
 96 | cm = confusion_matrix(Y_test, Y_pred)
 97 | c = print(cm[0, 0] + cm[1, 1])
 98 | 
 99 | 
100 | 
101 | 
102 | 
103 | 
104 | 
105 | 
106 | 


--------------------------------------------------------------------------------