From 48175b11be006e5584c9da07f798b03724da2f40 Mon Sep 17 00:00:00 2001
From: zgolebiewska <zgolebiewska5@gmail.com>
Date: Sun, 26 May 2024 14:23:37 +0200
Subject: [PATCH] IUM_07

---
 model.py | 69 +++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 41 insertions(+), 28 deletions(-)

diff --git a/model.py b/model.py
index f1633c8..f1df595 100644
--- a/model.py
+++ b/model.py
@@ -1,51 +1,64 @@
+from sacred import Experiment
+from sacred.observers import MongoObserver, FileStorageObserver
 import tensorflow as tf
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder, StandardScaler
 from sklearn.model_selection import train_test_split
 import json
-import mlflow
 
-mlflow.set_tracking_uri("http://localhost:5000")  # Ustawienie adresu MLflow Tracking Server
+ex = Experiment("s464906_experiment")
 
-df = pd.read_csv('OrangeQualityData.csv')
+mongo_url = "mongodb://admin:IUM_2021@tzietkiewicz.vm.wmi.amu.edu.pl:27017"
+ex.observers.append(MongoObserver(url=mongo_url, db_name='sacred'))
+ex.observers.append(FileStorageObserver('logs'))
 
-encoder = LabelEncoder()
-df["Color"] = encoder.fit_transform(df["Color"])
-df["Variety"] = encoder.fit_transform(df["Variety"])
-df["Blemishes"] = df["Blemishes (Y/N)"].apply(lambda x: 1 if x.startswith("Y") else 0)
+@ex.config
+def cfg():
+    epochs = 100
 
-df.drop(columns=["Blemishes (Y/N)"], inplace=True)
+@ex.automain
+def train_model(epochs):
+    df = pd.read_csv('OrangeQualityData.csv')
 
-X = df.drop(columns=["Quality (1-5)"])
-y = df["Quality (1-5)"]
+    encoder = LabelEncoder()
+    df["Color"] = encoder.fit_transform(df["Color"])
+    df["Variety"] = encoder.fit_transform(df["Variety"])
+    df["Blemishes"] = df["Blemishes (Y/N)"].apply(lambda x: 1 if x.startswith("Y") else 0)
 
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    df.drop(columns=["Blemishes (Y/N)"], inplace=True)
 
-scaler = StandardScaler()
-X_train_scaled = scaler.fit_transform(X_train)
-X_test_scaled = scaler.transform(X_test)
+    X = df.drop(columns=["Quality (1-5)"])
+    y = df["Quality (1-5)"]
 
-model = tf.keras.Sequential([
-    tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train_scaled.shape[1],)),
-    tf.keras.layers.Dense(32, activation='relu'),
-    tf.keras.layers.Dense(1)
-])
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-model.compile(optimizer='sgd', loss='mse')
+    scaler = StandardScaler()
+    X_train_scaled = scaler.fit_transform(X_train)
+    X_test_scaled = scaler.transform(X_test)
 
-with mlflow.start_run():
-    mlflow.log_param("optimizer", 'sgd')
-    mlflow.log_param("loss_function", 'mse')
-    mlflow.log_param("epochs", 100)
+    model = tf.keras.Sequential([
+        tf.keras.layers.Dense(64, activation='relu', input_shape=(X_train_scaled.shape[1],)),
+        tf.keras.layers.Dense(32, activation='relu'),
+        tf.keras.layers.Dense(1)
+    ])
 
-    history = model.fit(X_train_scaled, y_train, epochs=100, verbose=0, validation_data=(X_test_scaled, y_test))
+    model.compile(optimizer='sgd', loss='mse')
 
-    for key, value in history.history.items():
-        mlflow.log_metric(key, value[-1])  # Logujemy ostatnią wartość metryki
+    history = model.fit(X_train_scaled, y_train, epochs=epochs, verbose=0, validation_data=(X_test_scaled, y_test))
+
+    ex.log_scalar("epochs", epochs)
+
+    ex.add_artifact(__file__)
 
     model.save('orange_quality_model_tf.h5')
+    ex.add_artifact('orange_quality_model_tf.h5')
+
+    for key, value in history.history.items():
+        ex.log_scalar(key, value[-1])
 
     predictions = model.predict(X_test_scaled)
-
     with open('predictions_tf.json', 'w') as f:
         json.dump(predictions.tolist(), f, indent=4)
+    ex.add_artifact('predictions_tf.json')
+
+    return 'Training completed successfully'