add Jenkinsfile_train

.gitignore

@@ -1,2 +1,2 @@
 .idea
-*.csv
+

Jenkinsfile_train

@@ -0,0 +1,38 @@
+pipeline {
+  	agent {
+      dockerfile {
+			 additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} --build-arg CUTOFF=${params.CUTOFF} -t docker_image"
+		}
+	}
+	parameters {
+    string(
+            defaultValue: '1000',
+            description: 'Number of epochs',
+            name: 'EPOCHS',
+            trim: false
+        )
+   stages {
+    stage('Script'){
+      steps {
+        copyArtifacts filter: '*', projectName: 's444018-create-dataset'
+        sh 'python3 ./biblioteka_DL/dllib.py $EPOCHS'
+        archiveArtifacts artifacts: 'model.pkl', followSymlinks: false
+  			build job: 's444018-evaluation/master/'
+		      }
+	   }
+	}
+  post {
+      success {
+          emailext body: 'SUCCESS', subject: 's444018-training', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+      }
+      failure {
+          emailext body: 'FAILURE', subject: 's444018-training', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+      }
+      unstable {
+          emailext body: 'UNSTABLE', subject: 's444018-training', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+      }
+      changed {
+          emailext body: 'CHANGED', subject: 's444018-training', to: 'e19191c5.uam.onmicrosoft.com@emea.teams.ms'
+      }
+  }
+}

biblioteka_DL/dllib.py

@@ -1,3 +1,5 @@
+import sys
+
 import torch
 import torch.nn as nn
 import pandas as pd
@@ -54,7 +56,7 @@ def normalize_gross(imbd_data):
 
 
 def prepare_dataset():
-    df = pd.read_csv('../imdb_top_1000.csv')
+    df = pd.read_csv('imdb_top_1000.csv')
     df = drop_relevant_columns(df)
     df_lowercase = lowercase_columns_names(df)
     df = data_to_numeric(df_lowercase)
@@ -98,7 +100,9 @@ l = nn.MSELoss()
 optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
 
 
-num_epochs = 1000
+# num_epochs = 1000
+num_epochs = int(sys.argv[1])
+
 for epoch in range(num_epochs):
     # forward feed
     y_pred = model(X_train.requires_grad_())
@@ -123,6 +127,9 @@ predicted = model(X_train).detach().numpy()
 pred = pd.DataFrame(predicted)
 pred.to_csv('result.csv')
 
+# save model
+torch.save(model, "model.pkl")
+
 # plt.scatter(X_train.detach().numpy() , y_train.detach().numpy())
 # plt.plot(X_train.detach().numpy() , predicted , "red")
 # plt.xlabel("Meta_score")

lab5/Dockerfile

@@ -0,0 +1,29 @@
+FROM ubuntu:latest
+
+RUN apt-get update
+RUN apt-get install -y python3-pip
+RUN apt-get install -y unzip
+
+RUN pip3 install kaggle
+RUN pip3 install pandas
+RUN pip3 install sklearn
+RUN pip3 install numpy
+
+RUN pip3 install matplotlib
+RUN pip3 install torch
+
+ARG CUTOFF
+ARG KAGGLE_USERNAME
+ARG KAGGLE_KEY
+ENV CUTOFF=${CUTOFF}
+ENV KAGGLE_USERNAME=${KAGGLE_USERNAME}
+ENV KAGGLE_KEY=${KAGGLE_KEY}
+
+WORKDIR /app
+
+COPY lab2/download.sh .
+COPY biblioteka_DL/dllib.py .
+
+RUN chmod +x ./download.sh
+RUN ./download.sh
+#CMD python3 ./dllib.py

lab5/Jenkinsfile

@@ -0,0 +1,32 @@
+pipeline {
+  	agent {
+		dockerfile {
+			 additionalBuildArgs "--build-arg KAGGLE_USERNAME=${params.KAGGLE_USERNAME} --build-arg KAGGLE_KEY=${params.KAGGLE_KEY} --build-arg CUTOFF=${params.CUTOFF} -t docker_image"
+		}
+	}
+	parameters {
+        string(
+            defaultValue: 'szymonparafinski',
+            description: 'Kaggle username',
+            name: 'KAGGLE_USERNAME',
+            trim: false
+        )
+        password(
+            defaultValue: '',
+            description: 'Kaggle token taken from kaggle.json file, as described in https://github.com/Kaggle/kaggle-api#api-credentials',
+            name: 'KAGGLE_KEY'
+        )
+	string(
+            defaultValue: '100',
+            description: 'Cutoff lines',
+            name: 'CUTOFF'
+        )
+    }
+   stages {
+	stage('Script'){
+		steps {
+            			archiveArtifacts artifacts: 'data_test.csv, data_train.csv, data_dev.csv', followSymlinks: false
+		}
+	}
+	}
+}

lab5/Jenkinsfile_stats

@@ -0,0 +1,24 @@
+pipeline {
+    agent {
+	docker {
+		image 'docker_image'
+	}
+	}
+    parameters{
+        buildSelector(
+            defaultSelector: lastSuccessful(),
+            name: 'BUILD_SELECTOR',
+            description: 'Which build to use for copying artifacts'
+        )
+    }
+    stages {
+        stage("Script") {
+            steps {
+                copyArtifacts fingerprintArtifacts: true, projectName: 's444018-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+                sh 'chmod +x ./lab2/stats.sh'
+                sh "./lab2/stats.sh"
+                archiveArtifacts 'stats.txt'
+            }
+        }
+    }
+}

lab5/biblioteka_DL/dllib.py

@@ -0,0 +1,130 @@
+import torch
+import torch.nn as nn
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+
+
+def drop_relevant_columns(imbd_data):
+    imbd_data.drop(columns=["Poster_Link"], inplace=True)
+    imbd_data.drop(columns=["Overview"], inplace=True)
+    imbd_data.drop(columns=["Certificate"], inplace=True)
+    return imbd_data
+
+
+def lowercase_columns_names(imbd_data):
+    imbd_data["Series_Title"] = imbd_data["Series_Title"].str.lower()
+    imbd_data["Genre"] = imbd_data["Genre"].str.lower()
+    imbd_data["Director"] = imbd_data["Director"].str.lower()
+    imbd_data["Star1"] = imbd_data["Star1"].str.lower()
+    imbd_data["Star2"] = imbd_data["Star2"].str.lower()
+    imbd_data["Star3"] = imbd_data["Star3"].str.lower()
+    imbd_data["Star4"] = imbd_data["Star4"].str.lower()
+    return imbd_data
+
+
+def data_to_numeric(imbd_data):
+    imbd_data = imbd_data.replace(np.nan, '', regex=True)
+    imbd_data["Gross"] = imbd_data["Gross"].str.replace(',', '')
+    imbd_data["Gross"] = pd.to_numeric(imbd_data["Gross"], errors='coerce')
+    imbd_data["Runtime"] = imbd_data["Runtime"].str.replace(' min', '')
+    imbd_data["Runtime"] = pd.to_numeric(imbd_data["Runtime"], errors='coerce')
+    imbd_data["IMDB_Rating"] = pd.to_numeric(imbd_data["IMDB_Rating"], errors='coerce')
+    imbd_data["Meta_score"] = pd.to_numeric(imbd_data["Meta_score"], errors='coerce')
+    imbd_data["Released_Year"] = pd.to_numeric(imbd_data["Released_Year"], errors='coerce')
+    imbd_data = imbd_data.dropna()
+    imbd_data = imbd_data.reset_index()
+    imbd_data.drop(columns=["index"], inplace=True)
+    return imbd_data
+
+
+def create_train_dev_test(imbd_data):
+    data_train, data_test = train_test_split(imbd_data, test_size=230, random_state=1, shuffle=True)
+    data_test, data_dev = train_test_split(data_test, test_size=115, random_state=1, shuffle=True)
+    data_test.to_csv("data_test.csv", encoding="utf-8", index=False)
+    data_dev.to_csv("data_dev.csv", encoding="utf-8", index=False)
+    data_train.to_csv("data_train.csv", encoding="utf-8", index=False)
+
+
+def normalize_gross(imbd_data):
+    imbd_data[["Gross"]] = imbd_data[["Gross"]] / 10000000
+    return imbd_data
+
+
+def prepare_dataset():
+    df = pd.read_csv('../imdb_top_1000.csv')
+    df = drop_relevant_columns(df)
+    df_lowercase = lowercase_columns_names(df)
+    df = data_to_numeric(df_lowercase)
+    df = normalize_gross(df)
+    return df
+
+
+class LinearRegressionModel(torch.nn.Module):
+
+    def __init__(self):
+        super(LinearRegressionModel, self).__init__()
+        self.linear = torch.nn.Linear(1, 1)  # One in and one out
+
+    def forward(self, x):
+        y_pred = self.linear(x)
+        return y_pred
+
+
+df = prepare_dataset()
+data_train, data_test = train_test_split(df, random_state=1, shuffle=True)
+
+X_train = pd.DataFrame(data_train["Meta_score"], dtype=np.float64)
+X_train = X_train.to_numpy()
+
+y_train = pd.DataFrame(data_train["Gross"], dtype=np.float64)
+y_train = y_train.to_numpy()
+
+X_train = X_train.reshape(-1, 1)
+y_train = y_train.reshape(-1, 1)
+
+X_train = torch.from_numpy(X_train.astype(np.float32)).view(-1, 1)
+y_train = torch.from_numpy(y_train.astype(np.float32)).view(-1, 1)
+
+input_size = 1
+output_size = 1
+
+model = nn.Linear(input_size, output_size)
+
+learning_rate = 0.0001
+l = nn.MSELoss()
+optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
+
+
+num_epochs = 1000
+for epoch in range(num_epochs):
+    # forward feed
+    y_pred = model(X_train.requires_grad_())
+
+    # calculate the loss
+    loss = l(y_pred, y_train)
+
+    # backward propagation: calculate gradients
+    loss.backward()
+
+    # update the weights
+    optimizer.step()
+
+    # clear out the gradients from the last step loss.backward()
+    optimizer.zero_grad()
+
+    if epoch % 100 == 0:
+        print('epoch {}, loss {}'.format(epoch, loss.item()))
+
+predicted = model(X_train).detach().numpy()
+
+pred = pd.DataFrame(predicted)
+pred.to_csv('result.csv')
+
+# plt.scatter(X_train.detach().numpy() , y_train.detach().numpy())
+# plt.plot(X_train.detach().numpy() , predicted , "red")
+# plt.xlabel("Meta_score")
+# plt.ylabel("Gross")
+# plt.show()