From 999da6af3287505d898553f616302717fb89ce0c Mon Sep 17 00:00:00 2001
From: Wojciech Jarmosz <wojciech@jarmosz.com>
Date: Fri, 14 May 2021 00:20:04 +0200
Subject: [PATCH] Training script fixes

---
 .gitignore        | 6 +++++-
 Jenkinsfile       | 9 ++++++++-
 Jenkinsfile_stats | 7 -------
 training.py       | 5 +++--
 4 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/.gitignore b/.gitignore
index fc64530..ae6e931 100644
--- a/.gitignore
+++ b/.gitignore
@@ -149,4 +149,8 @@ Thumbs.db #thumbnail cache on Windows
 .prof
 
 env
-# End of https://www.toptal.com/developers/gitignore/api/python
\ No newline at end of file
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+/MoviesOnStreamingPlatforms_updated.train
+/MoviesOnStreamingPlatforms_updated.test
+/MoviesOnStreamingPlatforms_updated.dev
\ No newline at end of file
diff --git a/Jenkinsfile b/Jenkinsfile
index 3900438..ff593f9 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -22,5 +22,12 @@ stages {
             }
         }
     }
-    }       
+    }
+     post {
+      success {
+         build job: 's434704-training/master', parameters: [
+                string(name: 'options', value: "-shuffle=true")
+                ]
+      }
+   }       
 }
\ No newline at end of file
diff --git a/Jenkinsfile_stats b/Jenkinsfile_stats
index 138ade3..b37a194 100644
--- a/Jenkinsfile_stats
+++ b/Jenkinsfile_stats
@@ -19,11 +19,4 @@ pipeline {
             }
         }
     }
-    post {
-      success {
-         build job: 's434704-training/master', parameters: [
-                string(name: 'options', value: "-shuffle=true")
-                ]
-      }
-   }
 }
\ No newline at end of file
diff --git a/training.py b/training.py
index cddf32b..36c4832 100644
--- a/training.py
+++ b/training.py
@@ -9,9 +9,10 @@ from tensorflow.keras.layers.experimental import preprocessing
 
 pd.set_option("display.max_columns", None)
 
+cols = ['0','ID','Title','Year','Age','IMDb','Rotten Tomatoes','Netflix','Hulu','Prime Video','Disney+','Type','Directors','Genres','Country','Language','Runtime']
+
 # Wczytanie danych
-train_data = pd.read_csv("./train.csv")
-test_data = pd.read_csv("./test.csv")
+train_data = pd.read_csv("./MoviesOnStreamingPlatforms_updated.train", header=None, usecols=cols)
 
 # Stworzenie modelu 
 columns_to_use = ['Year', 'Runtime', 'Netflix']