import pandas as pd
# Sample data
data = {
'Pregnancies': [6, 1, 8, 1, 0, 5, 3, 10, 2, 8],
'Glucose': [148, 85, 183, 89, 137, 116, 78, 197, 125, 110],
'BloodPressure': [72, 66, 64, 66, 40, 74, 50, 70, 96, 92],
'SkinThickness': [35, 29, 0, 23, 35, 0, 32, 45, 0, 0],
'Insulin': [0, 0, 0, 94, 168, 0, 88, 543, 0, 0],
'BMI': [33.6, 26.6, 23.3, 28.1, 43.1, 25.6, 31.0, 30.5, 0.0, 37.6],
'DiabetesPedigreeFunction': [0.627, 0.351, 0.672, 0.167, 2.288, 0.201, 0.248, 0.158, 0.191, 0.191],
'Age': [50, 31, 32, 21, 33, 30, 26, 53, 54, 30],
'Outcome': [1, 0, 1, 0, 1, 0, 1, 1, 1, 0]
}
# Create DataFrame
df = pd.DataFrame(data)
# Aggregate data based on Glucose columns
aggregated_data = df.groupby(pd.cut(df['Glucose'], bins=[0, 100, 125, 150, 200])).mean()
print(aggregated_data)
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