From fb163e56532699146faf2eb4d8021134321cadc7 Mon Sep 17 00:00:00 2001
From: Anna Nowak <annadnowak98@gmail.com>
Date: Sun, 16 May 2021 23:41:55 +0200
Subject: [PATCH] MLflow

---
 .gitignore       |  3 ++-
 MLProject        | 11 +++++++++++
 evaluate.py      |  4 +++-
 requirements.txt |  3 ++-
 train.py         | 10 ++++++++--
 5 files changed, 26 insertions(+), 5 deletions(-)
 create mode 100644 MLProject

diff --git a/.gitignore b/.gitignore
index 629d54a..0a78817 100644
--- a/.gitignore
+++ b/.gitignore
@@ -64,4 +64,5 @@ dev.csv
 *.txt
 .venv/
 model.h5
-evaluation.png
\ No newline at end of file
+evaluation.png
+mlruns/*
\ No newline at end of file
diff --git a/MLProject b/MLProject
new file mode 100644
index 0000000..94bf167
--- /dev/null
+++ b/MLProject
@@ -0,0 +1,11 @@
+name: Fifa Players
+docker_env:
+   image:  docker.io/adnovac/ium_s434760:2.0 
+entry_points:
+  train:
+    parameters:
+      batch_size: {type: int, default: 15}
+      epochs: {type: int, default: 16}
+    command: "python train.py {batch_size} {epochs}"
+  evaluate:
+    command: "python evaluate.py"
\ No newline at end of file
diff --git a/evaluate.py b/evaluate.py
index ba37e89..2cf6247 100644
--- a/evaluate.py
+++ b/evaluate.py
@@ -2,8 +2,8 @@ import pandas as pd
 import numpy as np
 from os import path
 from tensorflow import keras
-import sys
 import matplotlib.pyplot as plt
+import mlflow
 
 model_name = "model.h5"
 
@@ -16,6 +16,8 @@ Y_test=test_data[["Overall"]].to_numpy()
 
 #MeanSquaredError
 results_test = model.evaluate(X_test, Y_test, batch_size=128)
+mlflow.log_metric("rmse", results_test)
+
 with open('results.txt', 'a+', encoding="UTF-8") as f:
     f.write(str(results_test) +"\n")
 
diff --git a/requirements.txt b/requirements.txt
index 454e683..0e6102a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -4,4 +4,5 @@ numpy==1.19.2
 sklearn
 tensorflow==2.4.1
 jinja2==2.11.3
-matplotlib
\ No newline at end of file
+matplotlib
+mlflow==1.17.0
\ No newline at end of file
diff --git a/train.py b/train.py
index 261fd61..4498904 100644
--- a/train.py
+++ b/train.py
@@ -2,6 +2,7 @@ import pandas as pd
 from os import path
 from tensorflow import keras
 from tensorflow.keras import layers
+import mlflow
 import sys
 
 model_name = "model.h5"
@@ -25,11 +26,16 @@ model.compile(
     loss=keras.losses.MeanSquaredError(),
 )
 
+batch_size = int(sys.argv[1])
+epochs = int(sys.argv[2])
+mlflow.log_param("batch_size", batch_size)
+mlflow.log_param("epochs", epochs)
+
 history = model.fit(
     X,
     Y,
-    batch_size=int(sys.argv[1]),
-    epochs=int(sys.argv[2]),
+    batch_size=batch_size,
+    epochs=epochs,
 )
 
 model.save(model_name)
\ No newline at end of file