From 2b853809be411313839af723f16dacdc36c7b5f4 Mon Sep 17 00:00:00 2001
From: Sheaza <nataliawolowiec3@gmail.com>
Date: Wed, 15 May 2024 00:30:21 +0200
Subject: [PATCH] fix mlflow

---
 MLFLOW/Dockerfile       | 13 +++++++++++++
 MLFLOW/requirements.txt |  3 +++
 MLFLOW/train.py         |  8 +++-----
 get_stats.py            |  6 +++---
 predict.py              |  2 +-
 5 files changed, 23 insertions(+), 9 deletions(-)
 create mode 100644 MLFLOW/Dockerfile
 create mode 100644 MLFLOW/requirements.txt

diff --git a/MLFLOW/Dockerfile b/MLFLOW/Dockerfile
new file mode 100644
index 0000000..fb2d6d7
--- /dev/null
+++ b/MLFLOW/Dockerfile
@@ -0,0 +1,13 @@
+FROM python:3.11
+
+RUN apt-get update && apt-get -y upgrade
+RUN apt-get install -y build-essential
+
+RUN python -m pip install --upgrade pip
+COPY ../requirements.txt /tmp
+RUN python -m pip install -r /tmp/requirements.txt
+
+WORKDIR ./app
+COPY train.py ./
+
+CMD bash
\ No newline at end of file
diff --git a/MLFLOW/requirements.txt b/MLFLOW/requirements.txt
new file mode 100644
index 0000000..2cb54be
--- /dev/null
+++ b/MLFLOW/requirements.txt
@@ -0,0 +1,3 @@
+pandas
+tensorflow
+mlflow
\ No newline at end of file
diff --git a/MLFLOW/train.py b/MLFLOW/train.py
index 9a2a74f..fb7b6e5 100644
--- a/MLFLOW/train.py
+++ b/MLFLOW/train.py
@@ -3,8 +3,6 @@ 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([
@@ -48,11 +46,11 @@ 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 = RegressionModel()
+    model.load_data("df_train.csv", "df_test.csv")
     model.train(epochs=int(args.epochs))
+    mlflow.log_param("epochs", int(args.epochs))
     rmse = model.evaluate()
-    mlflow.log_param("epoch", int(args.epochs))
     mlflow.log_metric("rmse", rmse)
 model.save_model()
diff --git a/get_stats.py b/get_stats.py
index 43fba39..2ca2b9d 100644
--- a/get_stats.py
+++ b/get_stats.py
@@ -5,9 +5,9 @@ pd.set_option('display.max_columns', None)
 pd.set_option('display.max_rows', None)
 
 
-df = pd.read_csv('./dataset.csv')
-df_train = pd.read_csv('./df_train.csv')
-df_test = pd.read_csv('./df_test.csv')
+df = pd.read_csv('MLFLOW/dataset.csv')
+df_train = pd.read_csv('MLFLOW/df_train.csv')
+df_test = pd.read_csv('MLFLOW/df_test.csv')
 
 
 with open('stats.txt', 'w') as f:
diff --git a/predict.py b/predict.py
index ff2c2c5..e48d7c0 100644
--- a/predict.py
+++ b/predict.py
@@ -6,7 +6,7 @@ import matplotlib.pyplot as plt
 
 np.set_printoptions(threshold=np.inf)
 
-data = pd.read_csv("df_test.csv")
+data = pd.read_csv("MLFLOW/df_test.csv")
 X_test = data.drop("Performance Index", axis=1)
 y_test = data["Performance Index"]