almost successfull ci/cd

.github/workflows/build.yaml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9"]
 
     steps:
       - run: echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
@@ -35,7 +35,8 @@ jobs:
           echo "PYTHONPATH=." >> $GITHUB_ENV
       - name: Lint with flake8
         run: |
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+          flake8 autotm --count --select=E9,F63,F7,F82 --show-source --statistics
       - name: Run test code
-        run: python examples/full_pipeline_example.py
+        run: |
+          pytest
       - run: echo "🍏 This job's status is ${{ job.status }}."

.gitignore

@@ -158,6 +158,8 @@ bigartm.*
 coverage_re/
 tests/integration/mlruns/*
 tests/integration/metrics
+*mlruns/*
+*metrics/*
 
 # sphinx docs
 docs/_build

autotm/algorithms_for_tuning/genetic_algorithm/ga.py

@@ -936,10 +936,7 @@ def run(self, verbose=False, visualize_results=False) -> Individual:
                         )
                         population[i] = elem
 
-            if (
-                self.num_fitness_evaluations
-                and self.evaluations_counter >= self.num_fitness_evaluations
-            ):
+            if self.num_fitness_evaluations and self.evaluations_counter >= self.num_fitness_evaluations:
                 self.metric_collector.save_fitness(
                     generation=ii,
                     params=[i.params for i in population],

autotm/preprocessing/text_preprocessing.py

@@ -15,6 +15,7 @@
 from nltk.stem import WordNetLemmatizer
 
 nltk.download("stopwords")
+nltk.download("wordnet")
 
 stop = stopwords.words("russian") + [" "] + stopwords.words("english")
 

pyproject.toml

@@ -16,24 +16,19 @@ packages = [
 
 
 [tool.poetry.dependencies]
-python = ">=3.8, <3.11"
+python = ">=3.8, <3.10"
 bigartm = "0.9.2"
 protobuf = "<=3.20.0"
 tqdm = "*"
 numpy = "*"
 PyYAML = "*"
-#Jinja2 = "3.1.2"
 dataclasses-json = "*"
 mlflow = "*"
 click = "*"
-#pymysql = "0.9.3"
-#psycopg2-binary = "2.8.5"
 pymongo = "*"
 scikit-learn = "*"
 scipy = "*"
 hyperopt = "*"
-#navec = "0.10.0"
-#seaborn = "0.11.0"
 pymystem3 = "*"
 nltk = "*"
 plotly = "*"
@@ -43,11 +38,8 @@ gensim = "*"
 pandas = "*"
 billiard = "*"
 pydantic = "*"
-#protobuf = "3.20.*"
 dill = "*"
 pytest = "*"
-#SALib = "~=1.4.7"
-#deap = "~=1.3.3"
 
 [tool.poetry.dev-dependencies]
 black = "*"

tests/integration/test_fit_predict.py

@@ -23,7 +23,7 @@ def check_predictions(autotm: AutoTM, df: pd.DataFrame, mixtures: ArrayLike):
 
 def test_fit_predict():
     # dataset with corpora to be processed
-    path_to_dataset = "../../data/sample_corpora/sample_dataset_lenta.csv"
+    path_to_dataset = "data/sample_corpora/sample_dataset_lenta.csv"
     alg_name = "ga"
 
     df = pd.read_csv(path_to_dataset)