First experiment

.dvc/.gitignore

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

.dvc/config

@@ -0,0 +1,5 @@
+[core]
+    analytics = false
+    remote = remote_storage
+['remote "remote_storage"']
+    url = /home/ajkumar/hackathonDVC/dvcDataStore

.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

data/prepared/.gitignore

@@ -0,0 +1,2 @@
+/train.csv
+/test.csv

data/prepared/test.csv.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 5151fcd60de0b43c2d18fde128ee5e09
+  size: 83326
+  path: test.csv

data/prepared/train.csv.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 0004b6e0e6d489f6902d6d6db47c24fe
+  size: 206725
+  path: train.csv

data/raw/.gitignore

@@ -0,0 +1,2 @@
+/train
+/val

data/raw/train.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: 7adc7abb69056f4d7afb512c78f2fce9.dir
+  size: 75309082
+  nfiles: 9470
+  path: train

data/raw/val.dvc

@@ -0,0 +1,5 @@
+outs:
+- md5: 0ad4dcf197b452735726bf8d8777201d.dir
+  size: 31248080
+  nfiles: 3925
+  path: val

metrics/accuracy.json

@@ -0,0 +1 @@
+{"accuracy": 0.7351077313054499}

model/.gitignore

@@ -0,0 +1 @@
+/model.joblib

model/model.joblib.dvc

@@ -0,0 +1,4 @@
+outs:
+- md5: 13c7384218e443fdf941f153ce53d134
+  size: 241222
+  path: model.joblib

src/train.py

@@ -37,7 +37,7 @@ def load_data(data_path):
 def main(repo_path):
     train_csv_path = repo_path / "data/prepared/train.csv"
     train_data, labels = load_data(train_csv_path)
-    sgd = SGDClassifier(max_iter=10)
+    sgd = SGDClassifier(max_iter=100)
     trained_model = sgd.fit(train_data, labels)
     dump(trained_model, repo_path / "model/model.joblib")