import pandas as pd
# import SAS file, your file location may be different
df = pd.read_sas(r'c:\temp\diabetes.sas7bdat')
# import Excel file
df = pd.read_excel(r'c:\temp\Diabetes.xlsx', sheet_name='Diabetes')
print(df)

# define the target variable (dependent variable) as y
y = df.Y_Binary

# import the library for partitioning the data into training and testing subsets
from sklearn.model_selection import train_test_split

# split the data into subsets
X_train, X_test, y_train, y_test = train_test_split(df, y, test_size=0.3)

# import support vector machine
from sklearn import svm
clf = svm.SVC(kernel='linear')

# propose a model using the training data set
clf.fit(X_train, y_train)

# Predict the outcome for the test dataset
y_pred = clf.predict(X_test)

# Import scikit-learn metrics module for accuracy evaluation
from sklearn import metrics

# Evalute odel Accuracy: What is the hit rate?
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

# Evalute model Precision: What percentage of positive are correctly identified?
print("Precision:",metrics.precision_score(y_test, y_pred))

# Evalute model Recall
print("Recall:",metrics.recall_score(y_test, y_pred))