parse dataframe

Author: frederikhoengaard

Pipfile

@@ -6,6 +6,7 @@ verify_ssl = true
 [packages]
 loguru = "==0.6.*"
 pandas = "==1.5.*"
+scikit-learn = "*"
 
 [dev-packages]
 black = "==23.*"

Pipfile.lock

@@ -0,0 +1,2 @@
+class DataSourceError(Exception):
+    """Raised if passing an incompatible argument as data source"""

python/src/lazylearn/errors/__init__.py

@@ -0,0 +1,18 @@
+from pipeline.pipeline import IngestionPipeline, PipelineStep
+
+
+class Ingestion:
+    def __init__(self):
+        pass
+
+    def run(self, data):
+        pipeline = IngestionPipeline()
+        pipeline.raw_data = data
+
+        pipeline.add(DataSourceParser(data))
+
+        pipeline.add(ColumnInterpreter())
+
+        pipeline.run()
+
+        return pipeline.response()

python/src/lazylearn/errors/errors.py

@@ -0,0 +1,21 @@
+from errors.errors import DataSourceError
+from pandas import DataFrame
+from pipeline.pipeline import IngestionPipeline, PipelineStep
+
+
+class DataSourceParser(PipelineStep):
+    def apply(self, pipeline: IngestionPipeline):
+        """
+        This method is responsible for parsing the raw data
+        source from its parent pipeline into a DataFrame
+        object.
+
+        :param pipeline: parent IngestionPipeline
+        :return:
+        """
+        assert pipeline.raw_data is not None
+
+        if isinstance(pipeline.raw_data, DataFrame):
+            pipeline.df = pipeline.raw_data
+        else:
+            raise DataSourceError

python/src/lazylearn/ingestion/ingestion_pipeline.py

@@ -0,0 +1,7 @@
+class LazyLearner:
+    def __init__(self):
+        self.project = None
+
+    def create_project(self, data, target, task="infer"):
+        # ingest data
+        pass

python/src/lazylearn/ingestion/ingestion_pipeline_steps/__init__.py

@@ -0,0 +1,32 @@
+from typing import List
+
+from models.models import Dataset
+from pandas import DataFrame
+
+
+class Pipeline:
+    def __init__(self):
+        self._has_run: bool = False
+        self._steps: List[PipelineStep] = []
+
+    def add(self, pipeline_step):
+        self._steps.append(pipeline_step)
+
+    def run(self):
+        [step.apply(self) for step in self._steps]
+        self._has_run = True
+
+
+class PipelineStep:
+    def apply(self, pipeline: Pipeline):
+        pass
+
+
+class IngestionPipeline(Pipeline):
+    def __init__(self):
+        super().__init__()
+        self.raw_data = None
+        self.df: DataFrame = None
+
+    def response(self):
+        return Dataset