From b77042df83edd46866eda890d4e2e16cbf4d798e Mon Sep 17 00:00:00 2001
From: Dominik Strzako <sylvaripl@gmail.com>
Date: Tue, 8 Jun 2021 00:28:23 +0200
Subject: [PATCH] dvc jenkins

---
 .gitignore          |  3 +++
 Jenkinsfile_dvc     | 17 ++++++++++++++++
 Zadanie_10_Split.py | 32 ++++++++++++++++++++++++++++++
 Zadanie_10_Train.py | 47 +++++++++++++++++++++++++++++++++++++++++++++
 dvc.lock            | 32 ++++++++++++++++++++++++++++++
 dvc.yaml            | 17 ++++++++++++++++
 6 files changed, 148 insertions(+)
 create mode 100644 Jenkinsfile_dvc
 create mode 100644 Zadanie_10_Split.py
 create mode 100644 Zadanie_10_Train.py
 create mode 100644 dvc.lock
 create mode 100644 dvc.yaml

diff --git a/.gitignore b/.gitignore
index 8a3fa50..063c393 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,4 @@
 /winequality-red.csv
+/10_x.csv
+/10_y.csv
+/sample.txt
diff --git a/Jenkinsfile_dvc b/Jenkinsfile_dvc
new file mode 100644
index 0000000..8b393e1
--- /dev/null
+++ b/Jenkinsfile_dvc
@@ -0,0 +1,17 @@
+pipeline {
+   agent {docker { image 'snowycocoon/ium_434788:3'}}  
+   stages {
+      stage('Test') {
+        steps {
+            sh 'echo hi'
+         }
+      }
+   }
+   post {
+        success {
+            mail body: 'SUCCESS',
+                subject: 's434788 DVC',
+                to: '26ab8f35.uam.onmicrosoft.com@emea.teams.ms'
+        }
+   }
+}
\ No newline at end of file
diff --git a/Zadanie_10_Split.py b/Zadanie_10_Split.py
new file mode 100644
index 0000000..fb74375
--- /dev/null
+++ b/Zadanie_10_Split.py
@@ -0,0 +1,32 @@
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+
+import numpy as np
+import pandas as pd
+
+wine=pd.read_csv('winequality-red.csv')
+
+y = wine['quality']
+x = wine.drop('quality', axis=1)
+
+citricacid = x['fixed acidity'] * x['citric acid']
+citric_acidity = pd.DataFrame(citricacid, columns=['citric_accidity'])
+density_acidity = x['fixed acidity'] * x['density']
+density_acidity = pd.DataFrame(density_acidity, columns=['density_acidity'])
+
+x = wine.join(citric_acidity).join(density_acidity)
+
+bins = (2, 5, 8)
+labels = ['bad', 'nice']
+y = pd.cut(y, bins = bins, labels = labels)
+
+enc = LabelEncoder()
+yenc = enc.fit_transform(y)
+
+scale = StandardScaler()
+scaled_x = scale.fit_transform(x)
+
+df_x = pd.DataFrame(scaled_x)
+df_y = pd.DataFrame(yenc)
+
+df_x.to_csv(r'10_x.csv', index=False)
+df_y.to_csv(r'10_y.csv', index=False)
\ No newline at end of file
diff --git a/Zadanie_10_Train.py b/Zadanie_10_Train.py
new file mode 100644
index 0000000..ef47596
--- /dev/null
+++ b/Zadanie_10_Train.py
@@ -0,0 +1,47 @@
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.optimizers import Adam
+
+
+from sklearn.metrics import accuracy_score
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler, LabelEncoder
+
+import numpy as np
+import pandas as pd
+
+x=pd.read_csv('10_x.csv')
+y=pd.read_csv('10_y.csv')
+
+x_train, x_test, y_train, y_test = train_test_split(x,y , test_size=0.2,train_size=0.8, random_state=21)
+
+NeuralModel = Sequential([
+                        Dense(128, activation='relu', input_shape=(14,)),
+                        Dense(32, activation='relu'),
+                        Dense(64, activation='relu'),
+                        Dense(64, activation='relu'),
+                        Dense(64, activation='relu'),
+                        Dense(1, activation='sigmoid')
+])
+
+
+#https://keras.io/api/losses/
+#https://keras.io/api/optimizers/
+#https://keras.io/api/metrics/
+
+opt = Adam(lr=0.0003)
+NeuralModel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy','AUC'])
+NeuralModel.fit(x_train, y_train, batch_size= 16, epochs = 16) #verbose = 1
+
+y_pred = NeuralModel.predict(x_test)
+y_pred = np.around(y_pred, decimals=0)
+results = accuracy_score(y_test,y_pred)
+
+
+text_file = open("sample.txt", "w")
+n = text_file.write(f"accuracy: {results}")
+text_file.close()
+
+print(f"accuracy: {results}")
+
+# Accuracy wynosi 1 z powodu banalnego podziału na 2 klasy jakosci Wina: "bad" i "nice".
\ No newline at end of file
diff --git a/dvc.lock b/dvc.lock
new file mode 100644
index 0000000..64ed1f0
--- /dev/null
+++ b/dvc.lock
@@ -0,0 +1,32 @@
+split_model:
+  cmd: python3 Zadanie_10_Split.py
+  deps:
+  - path: Zadanie_10_Split.py
+    md5: 2d95e0e1afc997823fc613788e2fbe16
+    size: 864
+  - path: winequality-red.csv
+    md5: 6a883fd98624e18c0b7ce251f4fab4fb
+    size: 100951
+  outs:
+  - path: 10_x.csv
+    md5: bcfb4f34de770b22e1065b9b2c133e16
+    size: 443481
+  - path: 10_y.csv
+    md5: 7d1dc704bd48248f8a51c771674e2ad8
+    size: 4800
+train_model:
+  cmd: python3 Zadanie_10_Train.py
+  deps:
+  - path: 10_x.csv
+    md5: bcfb4f34de770b22e1065b9b2c133e16
+    size: 443481
+  - path: 10_y.csv
+    md5: 7d1dc704bd48248f8a51c771674e2ad8
+    size: 4800
+  - path: Zadanie_10_Train.py
+    md5: 0d0aff9e327292b07cb5110c576f7efe
+    size: 1541
+  outs:
+  - path: sample.txt
+    md5: 98937548d721445b2095fb13deb756d7
+    size: 13
diff --git a/dvc.yaml b/dvc.yaml
new file mode 100644
index 0000000..2242f82
--- /dev/null
+++ b/dvc.yaml
@@ -0,0 +1,17 @@
+stages:
+  split_model:
+    cmd: python3 Zadanie_10_Split.py
+    deps:
+    - winequality-red.csv
+    - Zadanie_10_Split.py
+    outs:
+    - 10_x.csv
+    - 10_y.csv
+  train_model:
+    cmd: python3 Zadanie_10_Train.py
+    deps:
+    - Zadanie_10_Train.py
+    - 10_x.csv
+    - 10_y.csv
+    outs:
+    - sample.txt
\ No newline at end of file