Skip to content

Clean up format #7

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
qnoox wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Clean up format #7

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8610711
Clean up format
qnoox Oct 31, 2018
1c155c4
clean up format
qnoox Oct 31, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
211 changes: 120 additions & 91 deletions Pima.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,7 @@
#Python Code
#!/usr/bin/python
# -*- coding: utf-8 -*-
# Python Code

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
Expand All @@ -12,13 +15,13 @@
sns.countplot(x='Outcome', data=diab)
plt.show()

columns=diab.columns[:8]
columns = diab.columns[:8]
plt.subplots(figsize=(18, 15))
length=len(columns)
for i,j in itertools.zip_longest(columns,range(length)):
plt.subplot((length/2), 3, j+1)
length = len(columns)
for (i, j) in itertools.zip_longest(columns, range(length)):
plt.subplot(length / 2, 3, j + 1)
plt.subplots_adjust(wspace=0.2, hspace=0.5)
diab[i].hist(bins=20,edgecolor='black')
diab[i].hist(bins=20, edgecolor='black')
plt.title(i)
plt.show()

Expand All @@ -31,114 +34,140 @@
import warnings
warnings.filterwarnings('ignore')

outcome=diab['Outcome']
data=diab[diab.columns[:8]]
train,test=train_test_split(diab,test_size=0.25,random_state=0,stratify=diab['Outcome'])# stratify the outcome
train_X=train[train.columns[:8]]
test_X=test[test.columns[:8]]
train_Y=train['Outcome']
test_Y=test['Outcome']
outcome = diab['Outcome']
data = diab[diab.columns[:8]]
(train, test) = train_test_split(diab, test_size=0.25, random_state=0,
stratify=diab['Outcome']) # stratify the outcome
train_X = train[train.columns[:8]]
test_X = test[test.columns[:8]]
train_Y = train['Outcome']
test_Y = test['Outcome']

types=['rbf','linear']
types = ['rbf', 'linear']
for i in types:
model=svm.SVC(kernel=i)
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
print('Accuracy for SVM kernel=',i,'is',metrics.accuracy_score(prediction,test_Y))

model = svm.SVC(kernel=i)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print ('Accuracy for SVM kernel=', i, 'is',
metrics.accuracy_score(prediction, test_Y))

model = LogisticRegression()
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
print('The accuracy of the Logistic Regression is',metrics.accuracy_score(prediction,test_Y))

a_index=list(range(1,11))
a=pd.Series()
x=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
for i in list(range(1,11)):
model=KNeighborsClassifier(n_neighbors=i)
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
a=a.append(pd.Series(metrics.accuracy_score(prediction,test_Y)))
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print ('The accuracy of the Logistic Regression is',
metrics.accuracy_score(prediction, test_Y))

a_index = list(range(1, 11))
a = pd.Series()
x = [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
]
for i in list(range(1, 11)):
model = KNeighborsClassifier(n_neighbors=i)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
a = a.append(pd.Series(metrics.accuracy_score(prediction, test_Y)))
plt.plot(a_index, a)
plt.xticks(x)
plt.show()
print('Accuracies for different values of n are:',a.values)
print ('Accuracies for different values of n are:', a.values)

abc=[]
classifiers=['Linear Svm','Radial Svm','Logistic Regression','KNN']
models=[svm.SVC(kernel='linear'),svm.SVC(kernel='rbf'),LogisticRegression(),KNeighborsClassifier(n_neighbors=3)]
abc = []
classifiers = ['Linear Svm', 'Radial Svm', 'Logistic Regression', 'KNN']
models = [svm.SVC(kernel='linear'), svm.SVC(kernel='rbf'),
LogisticRegression(), KNeighborsClassifier(n_neighbors=3)]
for i in models:
model = i
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
abc.append(metrics.accuracy_score(prediction,test_Y))
models_dataframe=pd.DataFrame(abc,index=classifiers)
models_dataframe.columns=['Accuracy']
print(models_dataframe)

sns.heatmap(diab[diab.columns[:8]].corr(),annot=True,cmap='RdYlGn')
fig=plt.gcf()
fig.set_size_inches(10,8)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
abc.append(metrics.accuracy_score(prediction, test_Y))
models_dataframe = pd.DataFrame(abc, index=classifiers)
models_dataframe.columns = ['Accuracy']
print models_dataframe

sns.heatmap(diab[diab.columns[:8]].corr(), annot=True, cmap='RdYlGn')
fig = plt.gcf()
fig.set_size_inches(10, 8)
plt.show()

from sklearn.ensemble import RandomForestClassifier
model= RandomForestClassifier(n_estimators=100,random_state=0)
X=diab[diab.columns[:8]]
Y=diab['Outcome']
model.fit(X,Y)
print(pd.Series(model.feature_importances_,index=X.columns).sort_values(ascending=False))

diab2=diab[['Glucose','BMI','Age','DiabetesPedigreeFunction','Outcome']]
from sklearn.preprocessing import StandardScaler #Standardisation
features=diab2[diab2.columns[:4]]
features_standard=StandardScaler().fit_transform(features)# Gaussian Standardisation
x=pd.DataFrame(features_standard,columns=[['Glucose','BMI','Age','DiabetesPedigreeFunction']])
x['Outcome']=diab2['Outcome']
model = RandomForestClassifier(n_estimators=100, random_state=0)
X = diab[diab.columns[:8]]
Y = diab['Outcome']
model.fit(X, Y)
print pd.Series(model.feature_importances_,
index=X.columns).sort_values(ascending=False)

diab2 = diab[['Glucose', 'BMI', 'Age', 'DiabetesPedigreeFunction',
'Outcome']]
from sklearn.preprocessing import StandardScaler # Standardisation
features = diab2[diab2.columns[:4]]
features_standard = StandardScaler().fit_transform(features) # Gaussian Standardisation
x = pd.DataFrame(features_standard, columns=[['Glucose', 'BMI', 'Age',
'DiabetesPedigreeFunction']])
x['Outcome'] = diab2['Outcome']
outcome = x['Outcome']
train1,test1 = train_test_split(x,test_size=0.25,random_state=0,stratify=x['Outcome'])
(train1, test1) = train_test_split(x, test_size=0.25, random_state=0,
stratify=x['Outcome'])
train_X1 = train1[train1.columns[:4]]
test_X1 = test1[test1.columns[:4]]
train_Y1 = train1['Outcome']
test_Y1 = test1['Outcome']

abc=[]
classifiers=['Linear Svm','Radial Svm','Logistic Regression','KNN']
models=[svm.SVC(kernel='linear'),svm.SVC(kernel='rbf'),LogisticRegression(),KNeighborsClassifier(n_neighbors=3)]
abc = []
classifiers = ['Linear Svm', 'Radial Svm', 'Logistic Regression', 'KNN']
models = [svm.SVC(kernel='linear'), svm.SVC(kernel='rbf'),
LogisticRegression(), KNeighborsClassifier(n_neighbors=3)]
for i in models:
model = i
model.fit(train_X1,train_Y1)
prediction=model.predict(test_X1)
abc.append(metrics.accuracy_score(prediction,test_Y1))
new_models_dataframe=pd.DataFrame(abc,index=classifiers)
new_models_dataframe.columns=['New Accuracy']

new_models_dataframe=new_models_dataframe.merge(models_dataframe,left_index=True,right_index=True,how='left')
new_models_dataframe['Increase']=new_models_dataframe['New Accuracy']-new_models_dataframe['Accuracy']
print(new_models_dataframe)


from sklearn.model_selection import KFold #for K-fold cross validation
from sklearn.model_selection import cross_val_score #score evaluation

kfold = KFold(n_splits=10, random_state=22) # k=10, split the data into 10 equal parts

xyz=[]
accuracy=[]
classifiers=['Linear Svm','Radial Svm','Logistic Regression','KNN']
models=[svm.SVC(kernel='linear'),svm.SVC(kernel='rbf'),LogisticRegression(),KNeighborsClassifier(n_neighbors=3)]
model.fit(train_X1, train_Y1)
prediction = model.predict(test_X1)
abc.append(metrics.accuracy_score(prediction, test_Y1))
new_models_dataframe = pd.DataFrame(abc, index=classifiers)
new_models_dataframe.columns = ['New Accuracy']

new_models_dataframe = new_models_dataframe.merge(models_dataframe,
left_index=True, right_index=True, how='left')
new_models_dataframe['Increase'] = new_models_dataframe['New Accuracy'] \
- new_models_dataframe['Accuracy']
print new_models_dataframe

from sklearn.model_selection import KFold # for K-fold cross validation
from sklearn.model_selection import cross_val_score # score evaluation

kfold = KFold(n_splits=10, random_state=22) # k=10, split the data into 10 equal parts

xyz = []
accuracy = []
classifiers = ['Linear Svm', 'Radial Svm', 'Logistic Regression', 'KNN']
models = [svm.SVC(kernel='linear'), svm.SVC(kernel='rbf'),
LogisticRegression(), KNeighborsClassifier(n_neighbors=3)]
for i in models:
model = i
cv_result = cross_val_score(model,x[x.columns[:4]],x['Outcome'], cv = kfold,scoring = "accuracy")
cv_result=cv_result
cv_result = cross_val_score(model, x[x.columns[:4]], x['Outcome'],
cv=kfold, scoring='accuracy')
cv_result = cv_result
xyz.append(cv_result.mean())
accuracy.append(cv_result)
new_models_dataframe2 = pd.DataFrame(abc,index=classifiers)
new_models_dataframe2 = pd.DataFrame(abc, index=classifiers)
new_models_dataframe2.columns = ['CV Mean']
print(new_models_dataframe2)

linear_svc=svm.SVC(kernel='linear',C=0.1,gamma=10,probability=True)
lr=LogisticRegression(C=0.1)
ensemble_lin_lr=VotingClassifier(estimators=[('Linear_svm', linear_svc), ('Logistic Regression', lr)],
voting='soft', weights=[3,2]).fit(train_X1,train_Y1)
print('The accuracy for Linear SVM and Logistic Regression is:',ensemble_lin_lr.score(test_X1,test_Y1))
print new_models_dataframe2

linear_svc = svm.SVC(kernel='linear', C=0.1, gamma=10, probability=True)
lr = LogisticRegression(C=0.1)
ensemble_lin_lr = VotingClassifier(estimators=[('Linear_svm',
linear_svc), ('Logistic Regression',
lr)], voting='soft', weights=[3,
2]).fit(train_X1, train_Y1)
print ('The accuracy for Linear SVM and Logistic Regression is:',
ensemble_lin_lr.score(test_X1, test_Y1))
49 changes: 27 additions & 22 deletions newFeat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,6 @@
#!/usr/bin/python
# -*- coding: utf-8 -*-

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
Expand All @@ -6,13 +9,13 @@
diab = pd.read_csv('diabetes.csv')
diab.dropna(axis=0, how='any')
diab.isnull().sum()
'''diab.loc[:,'Sugar'] = pd.Series()'''
newFeat = diab['Glucose']*diab['BloodPressure']
newFeat2=diab['SkinThickness']*diab['Pregnancies']*0.5
idx=0
newFeat = diab['Glucose'] * diab['BloodPressure']
newFeat2 = diab['SkinThickness'] * diab['Pregnancies'] * 0.5
idx = 0
diab.insert(loc=8, column='Sugar', value=newFeat)
diab.insert(loc=diab.columns.get_loc('Outcome'), column='SkinFragile', value=newFeat2)
print(diab.head(5))
diab.insert(loc=diab.columns.get_loc('Outcome'), column='SkinFragile',
value=newFeat2)
print diab.head(5)

from sklearn import svm
from sklearn.neighbors import KNeighborsClassifier
Expand All @@ -23,23 +26,25 @@
import warnings
warnings.filterwarnings('ignore')

outcome=diab['Outcome']
data=diab[diab.columns[:10]]
train,test=train_test_split(diab,test_size=0.25,random_state=0,stratify=diab['Outcome'])# stratify the outcome
train_X=train[train.columns[:10]]
test_X=test[test.columns[:10]]
train_Y=train['Outcome']
test_Y=test['Outcome']
outcome = diab['Outcome']
data = diab[diab.columns[:10]]
(train, test) = train_test_split(diab, test_size=0.25, random_state=0,
stratify=diab['Outcome']) # stratify the outcome
train_X = train[train.columns[:10]]
test_X = test[test.columns[:10]]
train_Y = train['Outcome']
test_Y = test['Outcome']

types=['rbf','linear']
types = ['rbf', 'linear']
for i in types:
model=svm.SVC(kernel=i)
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
print('Accuracy for SVM kernel=',i,'is',metrics.accuracy_score(prediction,test_Y))

model = svm.SVC(kernel=i)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print ('Accuracy for SVM kernel=', i, 'is',
metrics.accuracy_score(prediction, test_Y))

model = LogisticRegression()
model.fit(train_X,train_Y)
prediction=model.predict(test_X)
print('The accuracy of the Logistic Regression is',metrics.accuracy_score(prediction,test_Y))
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print ('The accuracy of the Logistic Regression is',
metrics.accuracy_score(prediction, test_Y))