10/8/2020 Cancer
Meaningful Predictive Modeling Week-4 Assignment
CANCER DISEASE PREDICTION
In [1]:
#importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
In [16]:
#importing our cancer dataset
dataset = pd.read_csv('cancer.csv')
X = dataset.iloc[:, 2:31].values
Y = dataset.iloc[:, 1].values
In [17]:
dataset.head()
Out[17]:
842302 M 17.99 10.38 122.8 1001 0.1184 0.2776 0.3001 0.1471 ... 25.38
0 842517 M 20.57 17.77 132.90 1326.0 0.08474 0.07864 0.0869 0.07017 ... 24.99 2
1 84300903 M 19.69 21.25 130.00 1203.0 0.10960 0.15990 0.1974 0.12790 ... 23.57 2
2 84348301 M 11.42 20.38 77.58 386.1 0.14250 0.28390 0.2414 0.10520 ... 14.91 2
3 84358402 M 20.29 14.34 135.10 1297.0 0.10030 0.13280 0.1980 0.10430 ... 22.54
4 843786 M 12.45 15.70 82.57 477.1 0.12780 0.17000 0.1578 0.08089 ... 15.47 2
5 rows × 32 columns
In [18]:
print("Cancer data set dimensions : {}".format(dataset.shape))
Cancer data set dimensions : (568, 32)
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 1/6
10/8/2020 Cancer
In [19]:
dataset.isnull().sum()
dataset.isna().sum()
Out[19]:
842302 0
M 0
17.99 0
10.38 0
122.8 0
1001 0
0.1184 0
0.2776 0
0.3001 0
0.1471 0
0.2419 0
0.07871 0
1.095 0
0.9053 0
8.589 0
153.4 0
0.006399 0
0.04904 0
0.05373 0
0.01587 0
0.03003 0
0.006193 0
25.38 0
17.33 0
184.6 0
2019 0
0.1622 0
0.6656 0
0.7119 0
0.2654 0
0.4601 0
0.1189 0
dtype: int64
In [20]:
#Encoding categorical data values
from sklearn.preprocessing import LabelEncoder
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
In [21]:
# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.25, random_stat
e = 0)
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 2/6
10/8/2020 Cancer
In [22]:
#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 3/6
10/8/2020 Cancer
In [24]:
#Using Logistic Regression Algorithm to the Training Set
from sklearn.linear_model import LogisticRegression
classifier1 = LogisticRegression(random_state = 0)
classifier1.fit(X_train, Y_train)
#Using KNeighborsClassifier Method of neighbors class to use Nearest Neighbor algorithm
from sklearn.neighbors import KNeighborsClassifier
classifier2 = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
classifier2.fit(X_train, Y_train)
#Using SVC method of svm class to use Support Vector Machine Algorithm
from sklearn.svm import SVC
classifier3 = SVC(kernel = 'linear', random_state = 0)
classifier3.fit(X_train, Y_train)
#Using SVC method of svm class to use Kernel SVM Algorithm
from sklearn.svm import SVC
classifier4 = SVC(kernel = 'rbf', random_state = 0)
classifier4.fit(X_train, Y_train)
#Using GaussianNB method of naïve_bayes class to use Naïve Bayes Algorithm
from sklearn.naive_bayes import GaussianNB
classifier5 = GaussianNB()
classifier5.fit(X_train, Y_train)
#Using DecisionTreeClassifier of tree class to use Decision Tree Algorithm
from sklearn.tree import DecisionTreeClassifier
classifier6 = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)
classifier6.fit(X_train, Y_train)
#Using RandomForestClassifier method of ensemble class to use Random Forest Classificat
ion algorithm
from sklearn.ensemble import RandomForestClassifier
classifier7 = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_s
tate = 0)
classifier7.fit(X_train, Y_train)
C:\Users\ROHINI\Anaconda3\lib\site-packages\sklearn\linear_model\logistic.
py:432: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22.
Specify a solver to silence this warning.
FutureWarning)
Out[24]:
RandomForestClassifier(bootstrap=True, class_weight=None, criterion='entro
py',
max_depth=None, max_features='auto', max_leaf_nodes
=None,
min_impurity_decrease=0.0, min_impurity_split=None,
min_samples_leaf=1, min_samples_split=2,
min_weight_fraction_leaf=0.0, n_estimators=10,
n_jobs=None, oob_score=False, random_state=0, verbo
se=0,
warm_start=False)
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 4/6
10/8/2020 Cancer
In [29]:
Y_pred1 = classifier1.predict(X_test)
Y_pred2 = classifier2.predict(X_test)
Y_pred3 = classifier3.predict(X_test)
Y_pred4 = classifier4.predict(X_test)
Y_pred5 = classifier5.predict(X_test)
Y_pred6 = classifier6.predict(X_test)
Y_pred7 = classifier7.predict(X_test)
In [30]:
from sklearn.metrics import confusion_matrix
cm1 = confusion_matrix(Y_test, Y_pred1)
cm2 = confusion_matrix(Y_test, Y_pred2)
cm3 = confusion_matrix(Y_test, Y_pred3)
cm4 = confusion_matrix(Y_test, Y_pred4)
cm5 = confusion_matrix(Y_test, Y_pred5)
cm6 = confusion_matrix(Y_test, Y_pred6)
cm7 = confusion_matrix(Y_test, Y_pred7)
print(cm1)
print(cm2)
print(cm3)
print(cm4)
print(cm5)
print(cm6)
print(cm7)
[[91 1]
[ 2 48]]
[[91 1]
[ 6 44]]
[[90 2]
[ 4 46]]
[[92 0]
[ 6 44]]
[[89 3]
[ 6 44]]
[[84 8]
[ 6 44]]
[[89 3]
[ 6 44]]
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 5/6
10/8/2020 Cancer
In [34]:
from sklearn.metrics import accuracy_score
acc1=accuracy_score(Y_test, Y_pred1)*100
acc2=accuracy_score(Y_test, Y_pred2)*100
acc3=accuracy_score(Y_test, Y_pred3)*100
acc4=accuracy_score(Y_test, Y_pred4)*100
acc5=accuracy_score(Y_test, Y_pred5)*100
acc6=accuracy_score(Y_test, Y_pred6)*100
acc7=accuracy_score(Y_test, Y_pred7)*100
print("LogR",acc1)
print("KNN",acc2)
print("SVM",acc3)
print("K-SVM",acc4)
print("NB",acc5)
print("DT",acc6)
print("RF",acc7)
LogR 97.88732394366197
KNN 95.07042253521126
SVM 95.77464788732394
K-SVM 95.77464788732394
NB 93.66197183098592
DT 90.14084507042254
RF 93.66197183098592
In [38]:
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
import matplotlib.pyplot as plt
data = [acc1, acc2, acc3, acc4,acc5,acc6,acc7]
labels = ['LogR', 'KNN', 'SVM', 'KSVM', 'NB','DT','RF']
plt.xticks(range(len(data)), labels)
plt.xlabel('Algorithms')
plt.ylabel('Accuracy(%)')
plt.title('Comparision of Algorithms')
plt.bar(range(len(data)), data,color=['pink', 'red', 'green', 'blue', 'cyan','yellow',
'purple'])
plt.show()
localhost:8888/nbconvert/html/Desktop/Cancer.ipynb?download=false 6/6
