added data (DVC)

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,4 @@
+[core]
+    remote = ium_ssh_remote
+['remote "ium_ssh_remote"']
+    url = ssh://ium-sftp@tzietkiewicz.vm.wmi.amu.edu.pl/ium-sftp

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -17,3 +17,4 @@ metrics.png
 my_runs
 mlruns
 modelML
+/real-or-fake-fake-jobposting-prediction.zip

deepl.py

@@ -30,7 +30,7 @@ def train(epochs):
     # print(sys.argv[1])
     # epochs = int(sys.argv[1])
     # epochs=10
-    with zipfile.ZipFile('stare_zadania/real-or-fake-fake-jobposting-prediction.zip', 'r') as zip_ref:
+    with zipfile.ZipFile('real-or-fake-fake-jobposting-prediction.zip', 'r') as zip_ref:
         zip_ref.extractall('')
     mlflow.log_param("epochs", epochs)
 

real-or-fake-fake-jobposting-prediction.zip.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 720b87177496c52f028ec184935f8031
+  size: 16868281
+  path: real-or-fake-fake-jobposting-prediction.zip

requirements.txt

@@ -9,4 +9,5 @@ sklearn
 scipy
 sacred
 pymongo
-mlflow
+mlflow
+dvc