Pima Indians Diabetes Database
from IPython.display import HTML
HTML('''
<script>
function code_toggle() {
if (code_shown){
$('div.input').hide('500');
$('#toggleButton').val('Show Code')
} else {
$('div.input').show('500');
$('#toggleButton').val('Hide Code')
}
code_shown = !code_shown
}
$( document ).ready(function(){
code_shown=true;
});
</script>
<form action="javascript:code_toggle()"><input type="submit" id="toggleButton" value="Hide Code"></form>''')
import os
print(os.listdir("../input"))
Preprocessing
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
from keras.utils import np_utils
import warnings
warnings.filterwarnings('ignore')
df = pd.read_csv("../input/diabetes.csv")
#df = df.drop('Unnamed: 0', axis=1)
print(df.head())
print(df.shape)
print(df.columns)
Data Visualization
import seaborn as sns
import matplotlib.pyplot as plt
import seaborn as sns
corr=df.corr()
sns.heatmap(corr, xticklabels=corr.columns.values, yticklabels=corr.columns.values)
Machine Learning
# Thanks to: https://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process import GaussianProcessClassifier
from sklearn.gaussian_process.kernels import RBF
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.decomposition import PCA
h = .02 # step size in the mesh
names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Gaussian Process",
"Decision Tree", "Random Forest", "Neural Net", "AdaBoost",
"Naive Bayes", "QDA"]
classifiers = [
KNeighborsClassifier(3),
SVC(kernel="linear", C=0.025),
SVC(gamma=2, C=1),
GaussianProcessClassifier(1.0 * RBF(1.0)),
DecisionTreeClassifier(max_depth=5),
RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
MLPClassifier(alpha=1, max_iter=1000),
AdaBoostClassifier(),
GaussianNB(),
QuadraticDiscriminantAnalysis()]
X = df.drop(['Outcome'], axis = 1).values
pca = PCA(n_components=2,svd_solver='full')
X = pca.fit_transform(X)
y = df['Outcome']
# X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
# random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
#X += 2 * rng.uniform(size=X.shape)
#linearly_separable = (X, y)
datasets = [df]
figure = plt.figure(figsize=(27, 9))
i = 1
# iterate over datasets
for ds_cnt, ds in enumerate(datasets):
# preprocess dataset, split into training and test part
#X, y = ds
X = StandardScaler().fit_transform(X)
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=.3, random_state=42)
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
# just plot the dataset first
cm = plt.cm.RdBu
cm_bright = ListedColormap(['#FF0000', '#0000FF'])
ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
if ds_cnt == 0:
ax.set_title("Input data")
# Plot the training points
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
edgecolors='k')
# Plot the testing points
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6,
edgecolors='k')
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
i += 1
# iterate over classifiers
for name, clf in zip(names, classifiers):
ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
if hasattr(clf, "decision_function"):
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
else:
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
# Put the result into a color plot
Z = Z.reshape(xx.shape)
ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
# Plot the training points
ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright,
edgecolors='k')
# Plot the testing points
ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
edgecolors='k', alpha=0.6)
ax.set_xlim(xx.min(), xx.max())
ax.set_ylim(yy.min(), yy.max())
ax.set_xticks(())
ax.set_yticks(())
if ds_cnt == 0:
ax.set_title(name)
ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
size=15, horizontalalignment='right')
i += 1
plt.tight_layout()
plt.show()
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
X = df.drop(['Outcome'], axis = 1).values
Y = df['Outcome']
X = StandardScaler().fit_transform(X)
X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size = 0.30, random_state = 101)
# Preprocessing :
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import classification_report,confusion_matrix
from itertools import product
# Classifiers
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn import svm
from sklearn import tree
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
Logistic Regression
trainedmodel = LogisticRegression().fit(X_Train,Y_Train)
predictions =trainedmodel.predict(X_Test)
print(confusion_matrix(Y_Test,predictions))
print(classification_report(Y_Test,predictions))
Random Forest
trainedforest = RandomForestClassifier(n_estimators=700).fit(X_Train,Y_Train)
predictionforest = trainedforest.predict(X_Test)
print(confusion_matrix(Y_Test,predictionforest))
print(classification_report(Y_Test,predictionforest))
Support Vector Machines
trainedsvm = svm.LinearSVC().fit(X_Train, Y_Train)
predictionsvm = trainedsvm.predict(X_Test)
print(confusion_matrix(Y_Test,predictionsvm))
print(classification_report(Y_Test,predictionsvm))
Decision Tree
trainedtree = tree.DecisionTreeClassifier().fit(X_Train, Y_Train)
predictionstree = trainedtree.predict(X_Test)
print(confusion_matrix(Y_Test,predictionstree))
print(classification_report(Y_Test,predictionstree))
import graphviz
from sklearn.tree import DecisionTreeClassifier, export_graphviz
data = export_graphviz(trainedtree,out_file=None,feature_names=df.drop(['Outcome'], axis = 1).columns,
class_names=['0', '1'],
filled=True, rounded=True,
max_depth=2,
special_characters=True)
graph = graphviz.Source(data)
graph