import pandas as pd
from sklearn.model_selection import train_test_split
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score

df= pd.read_csv('diabetes.csv')
df.head()

	age	gender	sudden_weight_loss	genital_thrush	visual blurring	itching	irritability	delayed_healing	alopecia	obesity	result
0	40	Male	No	No	No	Yes	No	Yes	Yes	Yes	Positive
1	58	Male	No	No	Yes	No	No	No	Yes	No	Positive
2	41	Male	No	No	No	Yes	No	Yes	Yes	No	Positive
3	45	Male	Yes	Yes	No	Yes	No	Yes	No	No	Positive
4	60	Male	Yes	No	Yes	Yes	Yes	Yes	Yes	Yes	Positive

len(df)

520

#distribution of positive and negative
df['result'].value_counts()

	count
result
Positive	320
Negative	200

dtype: int64

sns.catplot(data=df,x='result',y='age', kind='box', hue='result')
plt.show()

#construct the features and label
features= df.iloc[:, 0:10]
features.head()

	age	gender	sudden_weight_loss	genital_thrush	visual blurring	itching	irritability	delayed_healing	alopecia	obesity
0	40	Male	No	No	No	Yes	No	Yes	Yes	Yes
1	58	Male	No	No	Yes	No	No	No	Yes	No
2	41	Male	No	No	No	Yes	No	Yes	Yes	No
3	45	Male	Yes	Yes	No	Yes	No	Yes	No	No
4	60	Male	Yes	No	Yes	Yes	Yes	Yes	Yes	Yes

label= df.iloc[:, -1]
label.head()

	result
0	Positive
1	Positive
2	Positive
3	Positive
4	Positive

dtype: object

# dummy variables
dm_feature= pd.get_dummies(data=features, drop_first=True, dtype=float)
dm_feature.head()

	age	gender_Male	sudden_weight_loss_Yes	genital_thrush_Yes	visual blurring_Yes	itching_Yes	irritability_Yes	delayed_healing_Yes	alopecia_Yes	obesity_Yes
0	40	1.0	0.0	0.0	0.0	1.0	0.0	1.0	1.0	1.0
1	58	1.0	0.0	0.0	1.0	0.0	0.0	0.0	1.0	0.0
2	41	1.0	0.0	0.0	0.0	1.0	0.0	1.0	1.0	0.0
3	45	1.0	1.0	1.0	0.0	1.0	0.0	1.0	0.0	0.0
4	60	1.0	1.0	0.0	1.0	1.0	1.0	1.0	1.0	1.0

#training and testing set , testing 20%
train_x, test_x, train_y, test_y= train_test_split(dm_feature, label, test_size=0.2, random_state=42)

#define naive bayes model
NB_model= MultinomialNB()
NB_model.fit(train_x, train_y)

MultinomialNB()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

pred_y= NB_model.predict(test_x)
print (pred_y[0:5]) #just looking at first 5 results

['Negative' 'Positive' 'Negative' 'Positive' 'Positive']

print(test_y[0:5]) #just looking at first 5 results

275    Negative
93     Positive
6      Positive
167    Positive
90     Positive
Name: result, dtype: object

#accuracy
accuracy_score = accuracy_score(test_y, pred_y)
accuracy_score

0.7884615384615384