Please evaluate my Python code and output:
In the Python file, you will be creating a model to predict the age of abalone’s from a subset of the abalone dataset which we provide in CSV format.
Part of the program is already implemented, your goal is to set up the model, train the model on the training data set, and print out some results.”
- “Python Age Prediction Project: In the Python file, you will be creating a model to predict the age of abalone’s from a subset of the abalone dataset which we provide in CSV format.”
- “Part of the program is already implemented, your goal is to set up the model, train the model on the training data set, and print out some results.”
- “These are the following details you need to implement: First, you’ll convert the feature dataset into a numpy array.”
- “Then you should create a Sequential model with 2 layers. The first layer should be a Dense layer with 64 units, and the second layer should also be a Dense one with units set to 1.”
- “Once the model is set up, you should compile it with a MeanSquaredError() loss and the optimizer set to optimizers.Adam().”
- “Then, when you fit the dataset on abalone_features and abalone_features, make sure to set the following values: epochs=10, verbose=0.”
- “Finally, you should print both the history from fitting the model, and the model summary.”
import pandas as pd
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers
abalone_train = pd.read_csv(
r"C:\Users\Anthony.DESKTOP-ES5HL78\Downloads\abalone.data",
sep=“,”,
names=[
“Sex”, “Length”, “Diameter”, “Height”, “Whole weight”,
“Shucked weight”, “Viscera weight”, “Shell weight”, “Age”
]
)
# Perform one-hot encoding for the ‘Sex’ column
abalone_train = pd.get_dummies(abalone_train, columns=[‘Sex’])
abalone_features = abalone_train.copy()
abalone_labels = abalone_features.pop(‘Age’)
# Convert to numpy array and float32 data type
abalone_features = abalone_features.astype(‘float32’)
abalone_labels = abalone_labels.astype(‘float32’)
# Create a sequential model
model = tf.keras.Sequential([
layers.Dense(64, activation=‘relu’),
layers.Dense(1)
])
# Compile the model
model.compile(optimizer=tf.keras.optimizers.Adam(), loss=tf.keras.losses.MeanSquaredError())
# Fit the model
history = model.fit(abalone_features, abalone_labels, epochs=10, verbose=0)
# Print history and model summary
print(history.history)
model.summary()
{ [74.98324584960938, 12.322690963745117, 7.765621185302734, 7.502653121948242, 7.229104518890381, 6.997042179107666, 6.799757957458496, 6.645227432250977, 6.521533489227295, 6.418800354003906]}
Model: “sequential”
---
# Layer (type) Output Shape Param #
dense (Dense) (None, 64) 704
dense_1 (Dense) (None, 1) 65
=================================================================
Total params: 769
Trainable params: 769
Non-trainable params: 0
## Data for this Question: [https://drive.google.com/file/d/1iSgWZUK…sp=sharing](https://drive.google.com/file/d/1iSgWZUK23Gw6R-2rUkKeEOl6BIwms8L8/view?usp=sharing)