m

MLproject

@@ -0,0 +1,11 @@
+name: 434695-mlflow
+
+docker_env:
+    image: shroomy/ium:1
+
+entry_points:
+    main:
+        parameters:
+            epochs: {type: int, default: 15}
+            batch_size: {type: int, default: 16}
+        command: "python3 vgsales-mlflow.py {epochs} {batch_size}"

train_evaluate/Dockerfile

@@ -5,27 +5,19 @@ FROM ubuntu:latest
 RUN apt update && apt install -y figlet
 RUN apt install -y git
 RUN apt install -y python3-pip
-RUN pip3 install --user setuptools
+RUN pip3 install  setuptools
-RUN pip3 install --user kaggle
+RUN pip3 install  kaggle
-RUN pip3 install --user pandas
+RUN pip3 install  pandas
-RUN pip3 install --user numpy
+RUN pip3 install  numpy
-RUN pip3 install --user seaborn
+RUN pip3 install  seaborn
-RUN pip3 install --user sklearn
+RUN pip3 install  sklearn
-RUN pip3 install --user matplotlib
+RUN pip3 install  matplotlib
-RUN pip3 install --user tensorflow
+RUN pip3 install  tensorflow
-RUN pip3 install --user sacred
+RUN pip3 install  sacred
-RUN pip3 install --user wget
+RUN pip3 install  wget
-RUN pip3 install --user keras
+RUN pip3 install  keras
-RUN pip3 install --user GitPython
+RUN pip3 install  GitPython
-RUN pip3 install --user pymongo
+RUN pip3 install  pymongo
+RUN pip3 install  mlflow
 
 
-WORKDIR /app
-
-COPY ./train.py ./
-COPY ./evaluate.py ./
-COPY ./sacred1.py ./
-COPY ./sacred2.py ./
-COPY ./skrypt.sh ./
-COPY ./zadanie2.py ./
-COPY ./zadanie5.py ./

vgsales-mlflow.py

@@ -0,0 +1,67 @@
+import sys
+from keras.backend import batch_dot, mean
+import pandas as pd
+import numpy as np
+from six import int2byte
+from sklearn import preprocessing
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+from sklearn.model_selection import train_test_split
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras.layers import Input, Dense, Activation,Dropout
+from tensorflow.keras.models import Model
+from tensorflow.keras.callbacks import EarlyStopping
+from tensorflow.keras.models import Sequential
+import mlflow
+
+
+
+def my_main(epochs, batch_size):
+
+    vgsales=pd.read_csv('vgsales.csv')
+
+    vgsales['Nintendo'] = vgsales['Publisher'].apply(lambda x: 1 if x=='Nintendo' else 0)
+
+    Y = vgsales['Nintendo']
+    X = vgsales.drop(['Rank','Name','Platform','Year','Genre','Publisher','Nintendo'],axis = 1)
+
+    X_train, X_test, y_train, y_test = train_test_split(X,Y , test_size=0.2,train_size=0.8, random_state=21)
+
+    model = Sequential()
+    model.add(Dense(9, input_dim = X_train, kernel_initializer='normal', activation='relu'))
+    model.add(Dense(1,kernel_initializer='normal', activation='sigmoid'))
+
+    early_stop = EarlyStopping(monitor="val_loss", mode="min", verbose=1, patience=10)
+
+
+    model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+
+    model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size, validation_data=(X_test, y_test))
+
+
+    prediction = model.predict(X_test)
+
+
+    rmse = mean_squared_error(y_test, prediction)
+
+
+    model.save('vgsales_model.h5')
+
+    return rmse, model
+
+
+
+epochs = int(sys.argv[1]) if len(sys.argv) > 1 else 15
+batch_size = int(sys.argv[2]) if len(sys.argv) > 2 else 16
+
+
+with mlflow.start_run():
+        
+    rmse, model = my_main(epochs, batch_size)
+
+    mlflow.log_param("epochs", epochs)
+    mlflow.log_param("batch_size", batch_size)
+    mlflow.log_metric("rmse", rmse) 
+    mlflow.keras.log_model(model, 'vgsales_model.h5')