Pima Indians Diabetes Database

In [1]:
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>''')
Out[1]:
In [2]:
import os
print(os.listdir("../input"))
['diabetes.csv']

Preprocessing

In [3]:
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
Using TensorFlow backend.
In [4]:
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)
Pregnancies  Glucose   ...     Age  Outcome
0            6      148   ...      50        1
1            1       85   ...      31        0
2            8      183   ...      32        1
3            1       89   ...      21        0
4            0      137   ...      33        1

[5 rows x 9 columns]
(768, 9)
Index(['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',
   'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome'],
  dtype='object')

Data Visualization

In [5]:
import seaborn as sns
import matplotlib.pyplot as plt
In [6]:
import seaborn as sns

corr=df.corr()
sns.heatmap(corr, xticklabels=corr.columns.values, yticklabels=corr.columns.values)
Out[6]:
<matplotlib.axes._subplots.AxesSubplot at 0x7f8574669390>

Machine Learning

In [7]:
# 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()
In [8]:
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)
In [9]:
# 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

In [10]:
trainedmodel = LogisticRegression().fit(X_Train,Y_Train)
predictions =trainedmodel.predict(X_Test)
print(confusion_matrix(Y_Test,predictions))
print(classification_report(Y_Test,predictions))
[[133  17]
[ 32  49]]
          precision    recall  f1-score   support

       0       0.81      0.89      0.84       150
       1       0.74      0.60      0.67        81

micro avg       0.79      0.79      0.79       231
macro avg       0.77      0.75      0.76       231
weighted avg       0.78      0.79      0.78       231

Random Forest

In [11]:
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))
[[130  20]
[ 30  51]]
          precision    recall  f1-score   support

       0       0.81      0.87      0.84       150
       1       0.72      0.63      0.67        81

micro avg       0.78      0.78      0.78       231
macro avg       0.77      0.75      0.75       231
weighted avg       0.78      0.78      0.78       231

Support Vector Machines

In [12]:
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))
[[133  17]
[ 33  48]]
          precision    recall  f1-score   support

       0       0.80      0.89      0.84       150
       1       0.74      0.59      0.66        81

micro avg       0.78      0.78      0.78       231
macro avg       0.77      0.74      0.75       231
weighted avg       0.78      0.78      0.78       231

/opt/conda/lib/python3.6/site-packages/sklearn/svm/base.py:931: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.
"the number of iterations.", ConvergenceWarning)

Decision Tree

In [13]:
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))
[[112  38]
[ 31  50]]
          precision    recall  f1-score   support

       0       0.78      0.75      0.76       150
       1       0.57      0.62      0.59        81

micro avg       0.70      0.70      0.70       231
macro avg       0.68      0.68      0.68       231
weighted avg       0.71      0.70      0.70       231

In [14]:
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
Out[14]:
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"> Tree 0 Glucose ≤ 1.052 gini = 0.454 samples = 537 value = [350, 187] class = 0 1 Age ≤ -0.488 gini = 0.387 samples = 453 value = [334, 119] class = 0 0->1 True 154 Age ≤ 2.234 gini = 0.308 samples = 84 value = [16, 68] class = 1 0->154 False 2 BMI ≤ -0.113 gini = 0.208 samples = 220 value = [194, 26] class = 0 1->2 57 Glucose ≤ -0.67 gini = 0.48 samples = 233 value = [140, 93] class = 0 1->57 3 (...) 2->3 14 (...) 2->14 58 (...) 57->58 71 (...) 57->71 155 Insulin ≤ 4.018 gini = 0.248 samples = 76 value = [11, 65] class = 1 154->155 182 BMI ≤ -0.164 gini = 0.469 samples = 8 value = [5, 3] class = 0 154->182 156 (...) 155->156 <