rama0519/DiabeticLogistic123

Logistic Regression Diabetes Prediction Model

Instructions for Users

DiabeticLogistic Model

This model predicts the likelihood of diabetes based on medical data using logistic regression.

Dataset

The model is trained on a dataset with features including:

• Glucose
• BloodPressure
• SkinThickness
• Insulin
• BMI
• DiabetesPedigreeFunction
• Age

Preprocessing

Features are normalized using StandardScaler.

Usage

Downloading the Model

!pip install pandas scikit-learn joblib huggingface_hub

from huggingface_hub import hf_hub_download
import joblib
import pandas as pd

# Your Hugging Face token
token = "put your token here"

# Download the model and scaler from the Hugging Face Hub using the token
model_path = hf_hub_download(repo_id="rama0519/DiabeticLogistic123", filename="logistic_regression_model.joblib", use_auth_token=token)
scaler_path = hf_hub_download(repo_id="rama0519/DiabeticLogistic123", filename="scaler.joblib", use_auth_token=token)

# Load the model and scaler
model = joblib.load(model_path)
scaler = joblib.load(scaler_path)

# Example data
data = pd.DataFrame({
    'Pregnancies': [6, 1],
    'Glucose': [148, 85],
    'BloodPressure': [72, 66],
    'SkinThickness': [35, 29],
    'Insulin': [0, 0],
    'BMI': [33.6, 26.6],
    'DiabetesPedigreeFunction': [0.627, 0.351],
    'Age': [50, 31]
})

# Normalize the data
data_scaled = scaler.transform(data)

# Make predictions
predictions = model.predict(data_scaled)
print("Predictions:", predictions)

Fine-Tuning the Model

To fine-tune the model, follow these steps:

Load the Model and Data

from huggingface_hub import hf_hub_download
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
import joblib

# Your Hugging Face token
token = "put your token here"

# Download the model and scaler from the Hugging Face Hub using the token
model_path = hf_hub_download(repo_id="rama0519/DiabeticLogistic123", filename="logistic_regression_model.joblib", use_auth_token=token)
scaler_path = hf_hub_download(repo_id="rama0519/DiabeticLogistic123", filename="scaler.joblib", use_auth_token=token)

# Load the model and scaler
model = joblib.load(model_path)
scaler = joblib.load(scaler_path)

# Load your dataset
data = pd.read_csv('/content/Healthcare-Diabetes.csv')

# Drop the 'Id' column if it exists
if 'Id' in data.columns:
    data = data.drop(columns=['Id'])

X = data.drop(columns=['Outcome'])
y = data['Outcome']

# Normalize the features
X_scaled = scaler.transform(X)

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

Fine-Tune the Model

# Fine-tune the model
model.fit(X_train, y_train)

# Evaluate the fine-tuned model
y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print(f'Fine-tuned Accuracy: {accuracy:.2f}')

Save the Fine-Tuned Model

joblib.dump(model, 'fine_tuned_logistic_regression_model.joblib')