add mlflow
All checks were successful
s464980-evaluation/pipeline/head This commit looks good
s464980-training/pipeline/head This commit looks good

This commit is contained in:
Sheaza 2024-05-15 00:12:58 +02:00
parent 1b646836f8
commit 32448bea84
5 changed files with 70 additions and 30 deletions

10
MLFLOW/MLproject Normal file
View File

@ -0,0 +1,10 @@
name: s464980
docker_env:
image: s464980-mlflow
entry_points:
main:
parameters:
epochs: float
command: "python train.py --epochs {epochs}"

58
MLFLOW/train.py Normal file
View File

@ -0,0 +1,58 @@
import pandas as pd
from tensorflow import keras
from tensorflow.keras import layers
import argparse
import mlflow
class RegressionModel:
def __init__(self, optimizer="adam", loss="mean_squared_error"):
self.model = keras.Sequential([
layers.Input(shape=(5,)), # Input layer
layers.Dense(32, activation='relu'), # Hidden layer with 32 neurons and ReLU activation
layers.Dense(1) # Output layer with a single neuron (for regression)
])
self.optimizer = optimizer
self.loss = loss
self.X_train = None
self.X_test = None
self.y_train = None
self.y_test = None
def load_data(self, train_path, test_path):
data_train = pd.read_csv(train_path)
data_test = pd.read_csv(test_path)
self.X_train = data_train.drop("Performance Index", axis=1)
self.y_train = data_train["Performance Index"]
self.X_test = data_test.drop("Performance Index", axis=1)
self.y_test = data_test["Performance Index"]
def train(self, epochs=30):
self.model.compile(optimizer=self.optimizer, loss=self.loss)
self.model.fit(self.X_train, self.y_train, epochs=epochs, batch_size=32, validation_data=(self.X_test, self.y_test))
def predict(self, data):
prediction = self.model.predict(data)
return prediction
def evaluate(self):
test_loss = self.model.evaluate(self.X_test, self.y_test)
print(f"Test Loss: {test_loss:.4f}")
return test_loss
def save_model(self):
self.model.save("model.keras")
parser = argparse.ArgumentParser()
parser.add_argument('--epochs')
args = parser.parse_args()
mlflow.set_tracking_uri("http://localhost:5000")
model = RegressionModel()
with mlflow.start_run() as run:
model.train(epochs=int(args.epochs))
rmse = model.evaluate()
mlflow.log_param("epoch", int(args.epochs))
mlflow.log_metric("rmse", rmse)
model.save_model()

View File

@ -1,9 +0,0 @@
name: s464980
conda_env: conda.yaml
entry_points:
optimal_parameters:
parameters:
epochs: { type: int, default: 20 }
command: 'python train.py {epochs}'

View File

@ -1,13 +0,0 @@
name: s464980
channels:
- defaults
dependencies:
- python=3.11
- pip
- pip:
- mlflow
- tensorflow
- pandas
- scikit-learn
- numpy
- matplotlib

View File

@ -2,8 +2,6 @@ import pandas as pd
from tensorflow import keras
from tensorflow.keras import layers
import argparse
import mlflow
class RegressionModel:
def __init__(self, optimizer="adam", loss="mean_squared_error"):
@ -48,11 +46,7 @@ parser = argparse.ArgumentParser()
parser.add_argument('--epochs')
args = parser.parse_args()
mlflow.set_tracking_uri("http://localhost:5000")
model = RegressionModel()
with mlflow.start_run() as run:
model.train(epochs=int(args.epochs))
rmse = model.evaluate()
mlflow.log_param("epoch", int(args.epochs))
mlflow.log_metric("rmse", rmse)
model.load_data("df_train.csv", "df_test.csv")
model.train(epochs=int(args.epochs))
model.save_model()