From 8c1d80c3d7b39a074cacdfe8514dc7d1a7171618 Mon Sep 17 00:00:00 2001
From: shishir kudchadker <shishir.kudchadker@gmail.com>
Date: Fri, 18 Nov 2022 07:32:49 +0530
Subject: [PATCH 1/4] First commit with setup and DVC files

---
 .dvc/.gitignore     | 3 +++
 .dvc/config         | 5 +++++
 .dvcignore          | 3 +++
 data/raw/.gitignore | 2 ++
 data/raw/train.dvc  | 5 +++++
 data/raw/val.dvc    | 5 +++++
 6 files changed, 23 insertions(+)
 create mode 100644 .dvc/.gitignore
 create mode 100644 .dvc/config
 create mode 100644 .dvcignore
 create mode 100644 data/raw/train.dvc
 create mode 100644 data/raw/val.dvc

diff --git a/.dvc/.gitignore b/.dvc/.gitignore
new file mode 100644
index 00000000..528f30c7
--- /dev/null
+++ b/.dvc/.gitignore
@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache
diff --git a/.dvc/config b/.dvc/config
new file mode 100644
index 00000000..7a5426e9
--- /dev/null
+++ b/.dvc/config
@@ -0,0 +1,5 @@
+[core]
+    analytics = false
+    remote = remote_storage
+['remote "remote_storage"']
+    url = /home/mlops/dvc_remote
diff --git a/.dvcignore b/.dvcignore
new file mode 100644
index 00000000..51973055
--- /dev/null
+++ b/.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
diff --git a/data/raw/.gitignore b/data/raw/.gitignore
index e69de29b..a5d9d98f 100644
--- a/data/raw/.gitignore
+++ b/data/raw/.gitignore
@@ -0,0 +1,2 @@
+/train
+/val
diff --git a/data/raw/train.dvc b/data/raw/train.dvc
new file mode 100644
index 00000000..14162364
--- /dev/null
+++ b/data/raw/train.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 7adc7abb69056f4d7afb512c78f2fce9.dir
+  size: 75309082
+  nfiles: 9470
+  path: train
diff --git a/data/raw/val.dvc b/data/raw/val.dvc
new file mode 100644
index 00000000..237148f4
--- /dev/null
+++ b/data/raw/val.dvc
@@ -0,0 +1,5 @@
+outs:
+- md5: 0ad4dcf197b452735726bf8d8777201d.dir
+  size: 31248080
+  nfiles: 3925
+  path: val

From f4617abbb94261487ce1e1a256bc3ec20268db20 Mon Sep 17 00:00:00 2001
From: shishir kudchadker <shishir.kudchadker@gmail.com>
Date: Sat, 19 Nov 2022 07:34:06 +0530
Subject: [PATCH 2/4] Created train and test csv files

---
 data/prepared/.gitignore    | 2 ++
 data/prepared/test.csv.dvc  | 4 ++++
 data/prepared/train.csv.dvc | 4 ++++
 3 files changed, 10 insertions(+)
 create mode 100644 data/prepared/test.csv.dvc
 create mode 100644 data/prepared/train.csv.dvc

diff --git a/data/prepared/.gitignore b/data/prepared/.gitignore
index e69de29b..22a65dd9 100644
--- a/data/prepared/.gitignore
+++ b/data/prepared/.gitignore
@@ -0,0 +1,2 @@
+/train.csv
+/test.csv
diff --git a/data/prepared/test.csv.dvc b/data/prepared/test.csv.dvc
new file mode 100644
index 00000000..3b350283
--- /dev/null
+++ b/data/prepared/test.csv.dvc
@@ -0,0 +1,4 @@
+outs:
+- md5: cbd4ba69ced15e40820a635e7e741627
+  size: 71491
+  path: test.csv
diff --git a/data/prepared/train.csv.dvc b/data/prepared/train.csv.dvc
new file mode 100644
index 00000000..ae08b157
--- /dev/null
+++ b/data/prepared/train.csv.dvc
@@ -0,0 +1,4 @@
+outs:
+- md5: 7f79cf9a4ab1316f7d7246d0b92ea16c
+  size: 178060
+  path: train.csv

From 2277f670cb34adb86a666ec24ff056becc3ad358 Mon Sep 17 00:00:00 2001
From: shishir kudchadker <shishir.kudchadker@gmail.com>
Date: Sat, 19 Nov 2022 17:27:59 +0530
Subject: [PATCH 3/4] Trained an SGD classifier

---
 model/.gitignore       | 1 +
 model/model.joblib.dvc | 4 ++++
 src/train.py           | 2 +-
 3 files changed, 6 insertions(+), 1 deletion(-)
 create mode 100644 model/model.joblib.dvc

diff --git a/model/.gitignore b/model/.gitignore
index e69de29b..565a9d50 100644
--- a/model/.gitignore
+++ b/model/.gitignore
@@ -0,0 +1 @@
+/model.joblib
diff --git a/model/model.joblib.dvc b/model/model.joblib.dvc
new file mode 100644
index 00000000..4b96d593
--- /dev/null
+++ b/model/model.joblib.dvc
@@ -0,0 +1,4 @@
+outs:
+- md5: 22490d1b369e3f7423c5b6ebd4db4234
+  size: 241075
+  path: model.joblib
diff --git a/src/train.py b/src/train.py
index e5feeda6..5d3c7c2c 100644
--- a/src/train.py
+++ b/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")
 

From 5d0b3e5928fa8b064c425df4e5025b43002f3516 Mon Sep 17 00:00:00 2001
From: shishir kudchadker <shishir.kudchadker@gmail.com>
Date: Sat, 19 Nov 2022 17:34:33 +0530
Subject: [PATCH 4/4] Evaluate the SGD MOdel accuracy

---
 metrics/accuracy.json | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 metrics/accuracy.json

diff --git a/metrics/accuracy.json b/metrics/accuracy.json
new file mode 100644
index 00000000..39176609
--- /dev/null
+++ b/metrics/accuracy.json
@@ -0,0 +1 @@
+{"accuracy": 0.7490494296577946}
\ No newline at end of file