Try a 40K dataset (4x data)

Author: dmpetrov

Diff for: data/data.xml.dvc

@@ -1,12 +1,13 @@
-md5: f5ea021eddd7b1df6de80b904cba1da6
+md5: 25c4a84510a41557840c61692dd14c11
 frozen: true
 deps:
 - path: get-started/data.xml
   repo:
     url: https://github.com/iterative/dataset-registry
-    rev_lock: f59388cd04276e75d70b2136597aaa27e7937cc3
+    rev_lock: cf6481baf56f156aa0876709cc231aaf3f3a3c29
+    rev: get-started-40K
 outs:
-- md5: 22a1a2931c8370d3aeedd7183606fd7f
-  size: 14445097
+- md5: 4bd325a30d5f1d5ea1a451d98767ddde
+  size: 59918667
   hash: md5
   path: data.xml

Diff for: dvc.lock

@@ -5,8 +5,8 @@ stages:
     deps:
     - path: data/data.xml
       hash: md5
-      md5: 22a1a2931c8370d3aeedd7183606fd7f
-      size: 14445097
+      md5: 4bd325a30d5f1d5ea1a451d98767ddde
+      size: 59918667
     - path: src/prepare.py
       hash: md5
       md5: f54d670ac8a4f63206781fc31d1f2651
@@ -18,38 +18,38 @@ stages:
     outs:
     - path: data/prepared
       hash: md5
-      md5: 153aad06d376b6595932470e459ef42a.dir
-      size: 8437363
+      md5: f8934609be51496ee500f80eea539c6f.dir
+      size: 35339221
       nfiles: 2
   featurize:
     cmd: python src/featurization.py data/prepared data/features
     deps:
     - path: data/prepared
       hash: md5
-      md5: 153aad06d376b6595932470e459ef42a.dir
-      size: 8437363
+      md5: f8934609be51496ee500f80eea539c6f.dir
+      size: 35339221
       nfiles: 2
     - path: src/featurization.py
       hash: md5
       md5: e22789fc9581cad11ef7a6fa3aa3f17b
       size: 4158
     params:
       params.yaml:
-        featurize.max_features: 200
+        featurize.max_features: 500
         featurize.ngrams: 2
     outs:
     - path: data/features
       hash: md5
-      md5: f35d4cc2c552ac959ae602162b8543f3.dir
-      size: 2232588
+      md5: 121056a1b192b22d31e15f61c8376928.dir
+      size: 12597137
       nfiles: 2
   train:
     cmd: python src/train.py data/features model.pkl
     deps:
     - path: data/features
       hash: md5
-      md5: f35d4cc2c552ac959ae602162b8543f3.dir
-      size: 2232588
+      md5: 121056a1b192b22d31e15f61c8376928.dir
+      size: 12597137
       nfiles: 2
     - path: src/train.py
       hash: md5
@@ -63,27 +63,27 @@ stages:
     outs:
     - path: model.pkl
       hash: md5
-      md5: d1f6e055f7f5e2827fcfae68d9b64d4c
-      size: 1958115
+      md5: 0af1d96a26c6bdaca6094842c4bc45f3
+      size: 3365729
   evaluate:
     cmd: python src/evaluate.py model.pkl data/features
     deps:
     - path: data/features
       hash: md5
-      md5: f35d4cc2c552ac959ae602162b8543f3.dir
-      size: 2232588
+      md5: 121056a1b192b22d31e15f61c8376928.dir
+      size: 12597137
       nfiles: 2
     - path: model.pkl
       hash: md5
-      md5: d1f6e055f7f5e2827fcfae68d9b64d4c
-      size: 1958115
+      md5: 0af1d96a26c6bdaca6094842c4bc45f3
+      size: 3365729
     - path: src/evaluate.py
       hash: md5
       md5: a1a59f55636170fb56e0c6afd3e28fa4
       size: 3315
     outs:
     - path: eval
       hash: md5
-      md5: 80a081570c800c60b9b98ca4b3c91dd7.dir
-      size: 1292342
+      md5: 53c957a76e8202d50581613c16c5ee93.dir
+      size: 4964257
       nfiles: 8

Diff for: params.yaml

@@ -3,7 +3,7 @@ prepare:
   seed: 20170428
 
 featurize:
-  max_features: 200
+  max_features: 500
   ngrams: 2
 
 train: