Merge branch '__rultor'

model/inference.py

@@ -0,0 +1,4 @@
+from predictor import Predictor
+
+prediction = Predictor().predict("invan/spring3-mvc-maven-json-hello-world")
+print(prediction)

model/predictor.py

@@ -25,13 +25,17 @@
 """
 from transformers import pipeline
 
+
 class Predictor:
-    def __init__(self, text):
-        self.text = text
+    def __init__(self, ref="h1alexbel/github-samples-classifier"):
+        self.ref = ref
 
-    def predict(self):
+    def predict(self, text):
         classifier = pipeline(
             "sentiment-analysis",
-            model="h1alexbel/github-samples-classifier"
+            model=self.ref
         )
-        return classifier(self.text)
+        return classifier(text)
+
+    def model(self):
+        return self.ref

objects/cli.py

@@ -27,6 +27,8 @@
 
 import typer
 
+from .filter_pipe import FilterPipe
+from model.predictor import Predictor
 from .dataset import Dataset
 from objects import NAME, VERSION
 from .pre_filter import PreFilter
@@ -44,7 +46,7 @@ def _version_callback(value: bool) -> None:
 @app.command()
 def filter(
         repositories: str = typer.Option(
-            ..., "--repositories", help="Path to the repositories CSV file."
+            ..., "--repositories", help="Path to the input repositories CSV file."
         ),
         out: str = typer.Option(
             ..., "--out", help="Path to the output CSV file."
@@ -53,18 +55,14 @@ def filter(
     """
     Filter repositories.
     """
-    typer.echo(f"Filtering {repositories}...")
-    # @todo #10:45min Filter the repositories using general-like interface.
-    #  We should execute filtering here using some general interface, so
-    #  it would easy to use either LLM or ML filters.
-    # @todo #19:45 Implement chain of csv transformation.
-    #  We should implement a transformation chain of csv files.
-    #  For now we are just adding separate objects to this script.
-    #  Let's create a class (let's call it `train` or `pipeline`) that would
-    #  execute all transformation one by one.
-    PreFilter(out).prepare()
-    Dataset(Input(repositories).copy()).formulate()
-    typer.echo(f"Filtering completed. Saving output to {out}...")
+    # @todo #18:30min Find effective way for processing readme.
+    #  For now we are not processing readme because of
+    #  <a href="https://github.com/h1alexbel/samples-filter/issues/39">this</a>.
+    #  We need to find actual way to process readme too since it can be crucial
+    #  data as model input. Let's study papers, outlined
+    #  <a href="https://github.com/yegor256/cam/issues/227#issue-2200080559">here</a>
+    #  first, rethink it and try to implement here.
+    FilterPipe(repositories, out, Predictor(), typer).apply()
 
 
 # Run it.

objects/feed.py

@@ -0,0 +1,40 @@
+# The MIT License (MIT)
+#
+# Copyright (c) 2024 Aliaksei Bialiauski
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+import csv
+
+"""
+Feed.
+"""
+
+
+class Feed:
+    def __init__(self, file):
+        self.file = file
+
+    def read(self):
+        with open(self.file, "r") as input:
+            reader = csv.DictReader(input)
+            feed = []
+            for row in reader:
+                name = row["full_name"]
+                feed.append(name)
+            return feed

objects/filter_pipe.py

@@ -0,0 +1,77 @@
+# The MIT License (MIT)
+#
+# Copyright (c) 2024 Aliaksei Bialiauski
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+import csv
+
+from .feed import Feed
+from .text_prediction import TextPrediction
+
+"""
+Filter pipe.
+"""
+
+
+class FilterPipe:
+    def __init__(self, repos, output, predictor, typer):
+        self.repos = repos
+        self.output = output
+        self.predictor = predictor
+        self.typer = typer
+
+    # @todo #18:60min Create integration test case for filter_pipe.py.
+    #  We should create some sort of integration test that checks filtering
+    #  together with model prediction, files creation and other things happening
+    #  in #apply(). Don't forget to remove this puzzle.
+    def apply(self):
+        self.typer.echo(f"Filtering {self.repos}...")
+        feed = Feed(self.repos).read()
+        with open("predictions.csv", "w") as predictions:
+            writer = csv.DictWriter(
+                predictions,
+                fieldnames=["candidate", "prediction", "model"]
+            )
+            writer.writeheader()
+            samples = []
+            self.typer.echo(
+                f"Predicting... (all predictions will be saved into {predictions.name})"
+            )
+            for candidate in feed:
+                prediction = self.predictor.predict(candidate)
+                log = {
+                    "candidate": candidate,
+                    "prediction": prediction,
+                    "model": self.predictor.model()
+                }
+                writer.writerow(log)
+                answer = TextPrediction(prediction).as_text()
+                self.typer.echo(f"{candidate} classified as {answer}")
+                if answer == "sample":
+                    samples.append(candidate)
+        self.typer.echo(f"found {len(samples)} samples")
+        with open(self.repos, "r") as source, open(self.output, "w") as target:
+            reader = csv.DictReader(source)
+            writer = csv.DictWriter(target, fieldnames=reader.fieldnames)
+            writer.writeheader()
+            for row in reader:
+                identifier = row["full_name"]
+                if identifier not in samples:
+                    writer.writerow(row)
+        self.typer.echo(f"Filtering completed. Output saved to {self.output}")

objects/text_prediction.py

@@ -0,0 +1,37 @@
+# The MIT License (MIT)
+#
+# Copyright (c) 2024 Aliaksei Bialiauski
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+"""
+Model prediction in simple text format.
+"""
+
+
+class TextPrediction:
+    def __init__(self, pred):
+        self.pred = pred
+
+    def as_text(self):
+        if self.pred[0]["label"] == "POSITIVE":
+            label = "sample"
+        else:
+            label = "real"
+        return label

tests/test_text_prediction.py

@@ -0,0 +1,57 @@
+# The MIT License (MIT)
+#
+# Copyright (c) 2024 Aliaksei Bialiauski
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+"""
+Test case for TextOut.
+"""
+import unittest
+
+from objects.text_prediction import TextPrediction
+
+
+class TestTextOut(unittest.TestCase):
+
+    def test_prints_as_real(self):
+        prediction = [{'label': 'NEGATIVE', 'score': 1.0}]
+        text = TextPrediction(prediction).as_text()
+        expected = "real"
+        self.assertEqual(
+            text,
+            expected,
+            f"output '{text}' for '{prediction}' does not match with expected {expected}"
+        )
+
+    def test_prints_as_sample(self):
+        prediction = [{'label': 'POSITIVE', 'score': 1.0}]
+        text = TextPrediction(prediction).as_text()
+        expected = "sample"
+        self.assertEqual(
+            text,
+            expected,
+            f"output '{text}' for '{prediction}' does not match with expected {expected}"
+        )
+
+    def test_raises_error_on_invalid_input(self):
+        with self.assertRaises(
+                TypeError,
+        ):
+            TextPrediction("<invalid input>").as_text()