import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
diabetes = pd.read_csv('diabetes.csv')
print(diabetes.columns)
Index(['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin',
'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome'],
dtype='object')
diabetes.head()
print("dimension of diabetes data: {}".format(diabetes.shape))
dimension of diabetes data: (768, 9)
print(diabetes.groupby('Outcome').size())
Outcome
0 500
1 268
dtype: int64
import seaborn as sns
sns.countplot(diabetes['Outcome'],label="Count")
diabetes.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 9 columns):
Pregnancies 768 non-null int64
Glucose 768 non-null int64
BloodPressure 768 non-null int64
SkinThickness 768 non-null int64
Insulin 768 non-null int64
BMI 768 non-null float64
DiabetesPedigreeFunction 768 non-null float64
Age 768 non-null int64
Outcome 768 non-null int64
dtypes: float64(2), int64(7)
memory usage: 54.1 KB
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(diabetes.loc[:, diabetes.columns != 'Outcome'], diabetes['Outcome'], stratify=diabetes['Outcome'], random_state=66)
from sklearn.neighbors import KNeighborsClassifier
training_accuracy = []
test_accuracy = []
# try n_neighbors from 1 to 10
neighbors_settings = range(1, 11)
for n_neighbors in neighbors_settings:
# build the model
knn = KNeighborsClassifier(n_neighbors=n_neighbors)
knn.fit(X_train, y_train)
# record training set accuracy
training_accuracy.append(knn.score(X_train, y_train))
# record test set accuracy
test_accuracy.append(knn.score(X_test, y_test))
plt.plot(neighbors_settings, training_accuracy, label="training accuracy")
plt.plot(neighbors_settings, test_accuracy, label="test accuracy")
plt.ylabel("Accuracy")
plt.xlabel("n_neighbors")
plt.legend()
plt.savefig('knn_compare_model')
knn = KNeighborsClassifier(n_neighbors=9)
knn.fit(X_train, y_train)
print('Accuracy of K-NN classifier on training set: {:.2f}'.format(knn.score(X_train, y_train)))
print('Accuracy of K-NN classifier on test set: {:.2f}'.format(knn.score(X_test, y_test)))
Accuracy of K-NN classifier on training set: 0.79
Accuracy of K-NN classifier on test set: 0.78
from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression().fit(X_train, y_train)
print("Training set accuracy: {:.3f}".format(logreg.score(X_train, y_train)))
print("Test set accuracy: {:.3f}".format(logreg.score(X_test, y_test)))
Training set accuracy: 0.781
Test set accuracy: 0.771
logreg001 = LogisticRegression(C=0.01).fit(X_train, y_train)
print("Training set accuracy: {:.3f}".format(logreg001.score(X_train, y_train)))
print("Test set accuracy: {:.3f}".format(logreg001.score(X_test, y_test)))
Training set accuracy: 0.700
Test set accuracy: 0.703
logreg100 = LogisticRegression(C=100).fit(X_train, y_train)
print("Training set accuracy: {:.3f}".format(logreg100.score(X_train, y_train)))
print("Test set accuracy: {:.3f}".format(logreg100.score(X_test, y_test)))
Training set accuracy: 0.785
Test set accuracy: 0.766
diabetes_features = [x for i,x in enumerate(diabetes.columns) if i!=8]
plt.figure(figsize=(8,6))
plt.plot(logreg.coef_.T, 'o', label="C=1")
plt.plot(logreg100.coef_.T, '^', label="C=100")
plt.plot(logreg001.coef_.T, 'v', label="C=0.001")
plt.xticks(range(diabetes.shape[1]), diabetes_features, rotation=90)
plt.hlines(0, 0, diabetes.shape[1])
plt.ylim(-5, 5)
plt.xlabel("Feature")
plt.ylabel("Coefficient magnitude")
plt.legend()
plt.savefig('log_coef')
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(random_state=0)
tree.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(tree.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(tree.score(X_test, y_test)))
Accuracy on training set: 1.000
Accuracy on test set: 0.714
tree = DecisionTreeClassifier(max_depth=3, random_state=0)
tree.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(tree.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(tree.score(X_test, y_test)))
Accuracy on training set: 0.773
Accuracy on test set: 0.740
print("Feature importances:\n{}".format(tree.feature_importances_))
Feature importances:
[ 0.04554275 0.6830362 0. 0. 0. 0.27142106
0. 0. ]
def plot_feature_importances_diabetes(model):
plt.figure(figsize=(8,6))
n_features = 8
plt.barh(range(n_features), model.feature_importances_, align='center')
plt.yticks(np.arange(n_features), diabetes_features)
plt.xlabel("Feature importance")
plt.ylabel("Feature")
plt.ylim(-1, n_features)
plot_feature_importances_diabetes(tree)
plt.savefig('feature_importance')
from sklearn.ensemble import RandomForestClassifier
rf = RandomForestClassifier(n_estimators=100, random_state=0)
rf.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(rf.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(rf.score(X_test, y_test)))
Accuracy on training set: 1.000
Accuracy on test set: 0.786
rf1 = RandomForestClassifier(max_depth=3, n_estimators=100, random_state=0)
rf1.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(rf1.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(rf1.score(X_test, y_test)))
Accuracy on training set: 0.800
Accuracy on test set: 0.755
plot_feature_importances_diabetes(rf)
from sklearn.ensemble import GradientBoostingClassifier
gb = GradientBoostingClassifier(random_state=0)
gb.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(gb.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(gb.score(X_test, y_test)))
Accuracy on training set: 0.917
Accuracy on test set: 0.792
gb1 = GradientBoostingClassifier(random_state=0, max_depth=1)
gb1.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(gb1.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(gb1.score(X_test, y_test)))
Accuracy on training set: 0.804
Accuracy on test set: 0.781
gb2 = GradientBoostingClassifier(random_state=0, learning_rate=0.01)
gb2.fit(X_train, y_train)
print("Accuracy on training set: {:.3f}".format(gb2.score(X_train, y_train)))
print("Accuracy on test set: {:.3f}".format(gb2.score(X_test, y_test)))
Accuracy on training set: 0.802
Accuracy on test set: 0.776
plot_feature_importances_diabetes(gb1)
from sklearn.svm import SVC
svc = SVC()
svc.fit(X_train, y_train)
print("Accuracy on training set: {:.2f}".format(svc.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(svc.score(X_test, y_test)))
Accuracy on training set: 1.00
Accuracy on test set: 0.65
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.fit_transform(X_test)
svc = SVC()
svc.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.2f}".format(svc.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.2f}".format(svc.score(X_test_scaled, y_test)))
Accuracy on training set: 0.77
Accuracy on test set: 0.77
svc = SVC(C=1000)
svc.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
svc.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(svc.score(X_test_scaled, y_test)))
Accuracy on training set: 0.790
Accuracy on test set: 0.797
from sklearn.neural_network import MLPClassifier
mlp = MLPClassifier(random_state=42)
mlp.fit(X_train, y_train)
print("Accuracy on training set: {:.2f}".format(mlp.score(X_train, y_train)))
print("Accuracy on test set: {:.2f}".format(mlp.score(X_test, y_test)))
Accuracy on training set: 0.71
Accuracy on test set: 0.67
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.fit_transform(X_test)
mlp = MLPClassifier(random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))
Accuracy on training set: 0.823
Accuracy on test set: 0.802
C:\Users\Susan\Anaconda3\lib\site-packages\sklearn\neural_network\multilayer_perceptron.py:564: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (200) reached and the optimization hasn't converged yet.
% self.max_iter, ConvergenceWarning)
mlp = MLPClassifier(max_iter=1000, random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))
Accuracy on training set: 0.877
Accuracy on test set: 0.755
mlp = MLPClassifier(max_iter=1000, alpha=1, random_state=0)
mlp.fit(X_train_scaled, y_train)
print("Accuracy on training set: {:.3f}".format(
mlp.score(X_train_scaled, y_train)))
print("Accuracy on test set: {:.3f}".format(mlp.score(X_test_scaled, y_test)))
Accuracy on training set: 0.795
Accuracy on test set: 0.792
plt.figure(figsize=(20, 5))
plt.imshow(mlp.coefs_[0], interpolation='none', cmap='viridis')
plt.yticks(range(8), diabetes_features)
plt.xlabel("Columns in weight matrix")
plt.ylabel("Input feature")
plt.colorbar()