Evaluate the Diabetes Dataset
Happy coding!
1: Import the dataset
#Import the required libraries
import pandas as pd
#Import the diabetes dataset
df_diabetes_data = pd.read_csv('C:\\Users\\kevin.zhang\\Lesson 8-2\\pima-indians-diabetes.data',header=None)
2: Analyze the dataset
#View the first five observations of the dataset
df_diabetes_data.head()
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 6 | 148 | 72 | 35 | 0 | 33.6 | 0.627 | 50 | 1 |
| 1 | 1 | 85 | 66 | 29 | 0 | 26.6 | 0.351 | 31 | 0 |
| 2 | 8 | 183 | 64 | 0 | 0 | 23.3 | 0.672 | 32 | 1 |
| 3 | 1 | 89 | 66 | 23 | 94 | 28.1 | 0.167 | 21 | 0 |
| 4 | 0 | 137 | 40 | 35 | 168 | 43.1 | 2.288 | 33 | 1 |
3: Find the features of the dataset
#Use the .NAMES file to view and set the features of the dataset
feature_names = ['Pregnant','Glucose','bp','skin','insulin','bmi','pedigree','age','label']
#Use the feature names set earlier and fix it as the column headers of the dataset
df_diabetes_data = pd.read_csv('C:\\Users\\kevin.zhang\\Lesson 8-2\\pima-indians-diabetes.data',header=None,names=feature_names)
#Verify if the dataset is updated with the new headers
df_diabetes_data.head()
.dataframe tbody tr th:only-of-type {
vertical-align: middle;
}
.dataframe tbody tr th {
vertical-align: top;
}
.dataframe thead th {
text-align: right;
}
| Pregnant | Glucose | bp | skin | insulin | bmi | pedigree | age | label | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 6 | 148 | 72 | 35 | 0 | 33.6 | 0.627 | 50 | 1 |
| 1 | 1 | 85 | 66 | 29 | 0 | 26.6 | 0.351 | 31 | 0 |
| 2 | 8 | 183 | 64 | 0 | 0 | 23.3 | 0.672 | 32 | 1 |
| 3 | 1 | 89 | 66 | 23 | 94 | 28.1 | 0.167 | 21 | 0 |
| 4 | 0 | 137 | 40 | 35 | 168 | 43.1 | 2.288 | 33 | 1 |
#View the number of observations and features of the dataset
df_diabetes_data.shape
(768, 9)
4: Find the response of the dataset
#Select features from the dataset to create the model
feature_select_cols = ['Pregnant','insulin','bmi','age']
#Create the feature object
X_feature = df_diabetes_data[feature_select_cols]
#Create the reponse object
Y_target = df_diabetes_data['label']
#View the shape of the feature object
X_feature.shape
(768, 4)
#View the shape of the target object
Y_target.shape
(768,)
5: Use training and testing datasets to train the model
#Split the dataset to test and train the model
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(X_feature,Y_target,random_state=1)
print(x_train.shape)
print(x_test.shape)
print(y_train.shape)
print(y_test.shape)
(576, 4)
(192, 4)
(576,)
(192,)
6: Create a model to predict the diabetes outcome
# Create a logistic regression model using the training set
from sklearn.linear_model import LogisticRegression
linreg = LogisticRegression()
linreg.fit(x_train,y_train)
LogisticRegression()
#Make predictions using the testing set
y_pred = linreg.predict(x_test)
7: Check the accuracy of the model
#Evaluate the accuracy of your model
from sklearn import metrics
print(metrics.accuracy_score(y_test,y_pred))
0.6927083333333334
#Print the first 30 actual and predicted responses
print('actual', y_test[0:30])
print('predict', y_pred[0:30])
actual 285 0
101 0
581 0
352 0
726 0
472 0
233 0
385 0
556 0
59 0
756 0
341 0
445 1
614 1
371 0
355 1
19 1
711 0
430 0
117 0
493 1
218 1
159 1
667 1
553 0
628 0
620 0
238 1
640 0
750 1
Name: label, dtype: int64
predict [0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0]
