From 197efd7bcbf0451e9bc9a9c1bf5d776e1a8e66e5 Mon Sep 17 00:00:00 2001
From: Zofia Galla <zosiagalla@gmail.com>
Date: Sun, 16 May 2021 22:25:46 +0200
Subject: [PATCH] Add MLflow

---
 Dockerfile               |  1 +
 Jenkinsfile              |  6 +++++
 MLproject                | 10 ++++++++
 ium_zadanie6_training.py | 53 ++++++++++++++++++++++------------------
 ium_zadanie8.py          | 46 ++++++++++++++++++++++++++++++++++
 5 files changed, 92 insertions(+), 24 deletions(-)
 create mode 100644 MLproject
 create mode 100644 ium_zadanie8.py

diff --git a/Dockerfile b/Dockerfile
index 7ccfd05..7247dc8 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -18,6 +18,7 @@ RUN pip3 install matplotlib
 RUN pip3 install --no-cache-dir tensorflow
 RUN pip3 install sacred
 RUN pip3 install pymongo
+RUN pip3 install mlflow
 
 CMD ./run.sh
 
diff --git a/Jenkinsfile b/Jenkinsfile
index 66a0895..3afefd2 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -18,4 +18,10 @@ pipeline {
 			}
 		}
     }
+	post {
+        success {
+
+            build job: 's434684-training/master'
+        }
+    }
 }
diff --git a/MLproject b/MLproject
new file mode 100644
index 0000000..a7883b6
--- /dev/null
+++ b/MLproject
@@ -0,0 +1,10 @@
+name: 434684-mlflow
+
+docker_env:
+    image: zollinka/ium:latest
+
+entry_points:
+    main:
+        parameters:
+            learning_rate: {type: float, default: 0.0001}
+        command: "python3 ium_zadanie6_training.py {learning_rate}"
\ No newline at end of file
diff --git a/ium_zadanie6_training.py b/ium_zadanie6_training.py
index d80cd15..15e4713 100644
--- a/ium_zadanie6_training.py
+++ b/ium_zadanie6_training.py
@@ -10,6 +10,7 @@ from sacred.observers import FileStorageObserver, MongoObserver
 from sacred import Experiment
 from sacred.observers import MongoObserver
 from datetime import datetime
+import mlflow
 
 
 ex = Experiment("434684", interactive=False, save_git_info=False)
@@ -23,34 +24,38 @@ def my_config():
 
 @ex.capture
 def prepare_train_model(learning_rate, _run):
-	_run.info["prepare_model"] = str(datetime.now())
+	with mlflow.start_run():
+		_run.info["prepare_model"] = str(datetime.now())
 
-	movies_train = pd.read_csv('movies_train.csv')
+		movies_train = pd.read_csv('movies_train.csv')
 
-	x_train = movies_train.copy()
-	y_train = x_train.pop('rottentomatoes_audience_score')
-	x_train.pop('Unnamed: 0')
+		x_train = movies_train.copy()
+		y_train = x_train.pop('rottentomatoes_audience_score')
+		x_train.pop('Unnamed: 0')
 
-	learning_rate = float(sys.argv[1])
-	model = Sequential()
-	model.add(layers.Input(shape=(22,)))
-	model.add(layers.Dense(64))
-	model.add(layers.Dense(64))
-	model.add(layers.Dense(32))
-	model.add(layers.Dense(1))
-
-	model.compile(loss='mean_absolute_error', optimizer=Adam(learning_rate))
-	
-	_run.info["train model"] = str(datetime.now())
-	
-	history = model.fit(
-		x = convert_to_tensor(x_train, np.float32),
-		y = y_train,
-		verbose=0, epochs=99)
+		learning_rate = float(sys.argv[1])
+		model = Sequential()
+		model.add(layers.Input(shape=(22,)))
+		model.add(layers.Dense(64))
+		model.add(layers.Dense(64))
+		model.add(layers.Dense(32))
+		model.add(layers.Dense(1))
 		
-	loss = history.history['loss'][-1]
-	_run.info["Loss"] = str(loss)
-	model.save('model_movies.h5')
+		mlflow.log_param("learning_rate", learning_rate)
+		
+		model.compile(loss='mean_absolute_error', optimizer=Adam(learning_rate))
+		
+		_run.info["train model"] = str(datetime.now())
+		
+		history = model.fit(
+			x = convert_to_tensor(x_train, np.float32),
+			y = y_train,
+			verbose=0, epochs=99)
+			
+		loss = history.history['loss'][-1]
+		_run.info["Loss"] = str(loss)
+		mlflow.log_metric("Loss", loss)
+		model.save('model_movies.h5')
 		
 
 @ex.main
diff --git a/ium_zadanie8.py b/ium_zadanie8.py
new file mode 100644
index 0000000..b10b484
--- /dev/null
+++ b/ium_zadanie8.py
@@ -0,0 +1,46 @@
+import sys
+from tensorflow.keras import layers, Sequential
+# from keras.layers import Flatten,Dense,Dropout, GlobalAveragePooling2D
+from tensorflow.keras.optimizers import Adam
+from tensorflow import convert_to_tensor
+import numpy as np
+import pandas as pd
+from sklearn.metrics import mean_squared_error
+from sacred.observers import FileStorageObserver, MongoObserver
+from sacred import Experiment
+from sacred.observers import MongoObserver
+from datetime import datetime
+import mlflow
+
+with mlflow.start_run():
+	learning_rate = float(sys.argv[1])
+
+	movies_train = pd.read_csv('movies_train.csv')
+
+	x_train = movies_train.copy()
+	y_train = x_train.pop('rottentomatoes_audience_score')
+	x_train.pop('Unnamed: 0')
+
+	learning_rate = float(sys.argv[1])
+	model = Sequential()
+	model.add(layers.Input(shape=(22,)))
+	model.add(layers.Dense(64))
+	model.add(layers.Dense(64))
+	model.add(layers.Dense(32))
+	model.add(layers.Dense(1))
+	
+	mlflow.log_param("learning_rate", learning_rate)
+	
+	model.compile(loss='mean_absolute_error', optimizer=Adam(learning_rate))
+	
+	
+	history = model.fit(
+		x = convert_to_tensor(x_train, np.float32),
+		y = y_train,
+		verbose=0, epochs=99)
+		
+	loss = history.history['loss'][-1]
+	
+	mlflow.log_metric("Loss", loss)
+	model.save('model_movies.h5')
+