Joelcio ETL Homework

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -16,4 +16,24 @@ Follow industry standards for each data type when decided on the final format fo
 * For dimensions without units, assume inches. Convert anything which isn't in inches to inches.
 * For weights without units, assume pounds. Convert anything which isn't in pounds to pounds.
 * UPC / Gtin / EAN should be handled as strings
-* Floating point and decimal numbers should preserve as much precision as possible
+* Floating point and decimal numbers should preserve as much precision as possible
+
+## Run ETL
+
+### Requirements
+- Python 3.10 
+
+### Install dependencies
+
+```bash
+pip install -r requirements.txt 
+```
+### Usage
+
+```
+python3 run_etl.py 
+```
+#### Can pass the filepath
+```
+python3 run_etl.py filepath
+```

elt_homework/__init__.py

@@ -0,0 +1,4 @@
+import logging
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

elt_homework/csv_reader.py

@@ -0,0 +1,27 @@
+import logging
+import pandas as pd
+
+logger = logging.getLogger(__name__)
+
+class CSVReader:
+    def __init__(self):
+        pass
+
+    def read_csv(self, file_path, columns):
+        """
+        Reads a CSV file using pandas.
+
+        Args:
+        - file_path (str): Path to the CSV file.
+        - columns (list): List of only columns to load
+
+        Returns:
+        - DataFrame: The DataFrame containing the CSV data.
+        """
+        try:
+            return pd.read_csv(file_path, usecols=columns, engine='python')
+        except Exception as e:
+            logger.exception("An error occurred:", e)
+
+
+

elt_homework/elt_processor.py

@@ -0,0 +1,82 @@
+
+import logging
+
+import country_converter as coco
+import numpy as np
+import pandas as pd
+
+from elt_homework.csv_reader import CSVReader
+from elt_homework.mapping import columns_mapping, output_columns
+from elt_homework.schema import ProductSchema
+
+logger = logging.getLogger(__name__)
+
+cc = coco.CountryConverter()
+
+class ETL:
+    def __init__(self):
+        self._csv_reader = CSVReader()
+
+    def _read_data(self, file_path):
+        """
+        Reads a CSV file and performs ETL operations with the useful columns
+
+        Args:
+        - file_path (str): Path to the CSV file.
+        """
+        logger.info(f'Reading {file_path} file')
+        return self._csv_reader.read_csv(file_path, columns_mapping.keys())
+
+    def _transformations(self, df):
+
+        def yes_no_to_bool(v):
+            if isinstance(v, str):
+                return v.lower() == 'yes' 
+            return False
+        # to bool
+        df['attrib__outdoor_safe'] = df['attrib__outdoor_safe'].apply(yes_no_to_bool)
+        df['attrib__kit'] = df['attrib__kit'].apply(yes_no_to_bool)
+        df['attrib__bulb_included'] = df['attrib__bulb_included'].apply(yes_no_to_bool)
+        # to int
+        df['attrib__number_bulbs'] = df['attrib__number_bulbs'].fillna(0).astype(int)
+        df['product__multipack_quantity'] = df['product__multipack_quantity'].fillna(0).astype(int)
+        # to str
+        df['ean13'] = df['ean13'].astype(str)
+        # contry:
+        df['product__country_of_origin__alpha_3'] = cc.pandas_convert( \
+             series=df['product__country_of_origin__alpha_3'], to='ISO3',not_found= np.NaN)
+        # currency:
+        df['cost_price'] = df['cost_price'].replace('[\$,]', '', regex=True).astype(float).round(2)
+
+        return df
+
+    def process(self, file_path):
+
+        # Read csv from file_path
+        df = self._read_data(file_path)
+
+        # Rename the columns according to the mapping
+        df.rename(columns=columns_mapping, inplace=True)
+
+        # Apply the transformations
+        df = self._transformations(df)
+
+        try:
+            ProductSchema.validate(df)
+        except Exception as ex:
+        # TODO alert system monitoring,
+        #It may be that the supplier/partner has changed something
+            raise ex
+
+        # Load all columns
+        output_df = pd.DataFrame(columns=output_columns)
+
+        # Fill the blank df columns with the existing data
+        for column in df.columns:
+            output_df[column] = df[column]
+        # Write csv
+        output_df.to_csv("output.csv", index=False)
+
+        logger.info(f'ETL finished, {output_df.shape[0]} rows,{output_df.shape[1]} cols saved')
+
+