simple_neural_network_project_1.py

# -*- coding: utf-8 -*-
"""simple neural network project 1.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1CZ_UB0_kjyY50bNs3D2BSBqcS56xR3hg
"""

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from keras.models import Sequential
from keras.layers import Dense


# Load the dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv"
data = pd.read_csv(url, sep=';')

# Display the first few rows of the dataset
print(data.head())

# Check for missing values
print(data.isnull().sum())

# Split features and target variable
X = data.drop('quality', axis=1)
y = data['quality']

# Split the data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Now X_train_scaled and X_test_scaled contain the preprocessed features
model = Sequential()
model.add(Dense(64, input_shape=(X_train.shape[1],), activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(1))  # For regression, as it's predicting wine quality (a regression task)

# Compile the model
model.compile(optimizer='adam', loss='mean_squared_error')  # Using Mean Squared Error as the loss function for regression

# Train the model
model.fit(X_train_scaled, y_train, epochs=50, batch_size=32, validation_split=0.1)

# Evaluate the model on test data
loss = model.evaluate(X_test_scaled, y_test)
print("Test Loss:", loss)