Merge pull request #24 from gizatechxyz/feature/giza_namespace

add Giza as a namespace package

.github/workflows/onpush.yml

@@ -27,7 +27,7 @@ jobs:
           poetry install
       - name: Lint with ruff
         run: |
-          poetry run ruff giza_datasets
+          poetry run ruff giza
       # Bring back when tests area working
       # - name: Testing
       #   run: |

.github/workflows/onrelease.yml

@@ -30,7 +30,7 @@ jobs:
             poetry install
       - name: Lint with ruff
         run: |
-            poetry run ruff giza_datasets
+            poetry run ruff giza
       - name: Build dist
         run: poetry build
       - name: Publish a Python distribution to PyPI

README.md

@@ -22,7 +22,7 @@ To get started with Giza Datasets, follow the steps below:
    ```
 2. Import the `DatasetsLoader` class and initialize it:
    ```python
-   from giza_datasets import DatasetsLoader
+   from giza.datasets import DatasetsLoader
    loader = DatasetsLoader()
    ```
 3. Optional: Depending on your device's configuration, it may be necessary to provide SSL certificates to verify the authenticity of HTTPS connections. You can ensure that all these certifications are correct by executing the following line of code:
@@ -56,7 +56,7 @@ To get started with the `DatasetsHub` class, follow the steps below:
 
 1. Import the `DatasetsHub` class and initialize it:
    ```python
-   from giza_datasets import DatasetsHub
+   from giza.datasets import DatasetsHub
    hub = DatasetsHub()
    ```
 2. Use the `show` method to print a table of all datasets in the hub:

giza/datasets/__init__.py

@@ -0,0 +1,4 @@
+from giza.datasets.hub import DatasetsHub
+from giza.datasets.loaders import DatasetsLoader
+
+__all__ = ["DatasetsLoader", "DatasetsHub"]

giza_datasets/cache_manager.py → giza/datasets/cache_manager.py

@@ -1,6 +1,7 @@
+import os
+
 import polars as pl
 import pyarrow.dataset as ds
-import os
 
 
 class CacheManager:

giza_datasets/constants.py → giza/datasets/constants.py

@@ -1,5 +1,5 @@
-from giza_datasets.defillama_constants import DEFILLAMA_SUPPORTED_PROJECTS
-from giza_datasets.models import Dataset
+from giza.datasets.defillama_constants import DEFILLAMA_SUPPORTED_PROJECTS
+from giza.datasets.models import Dataset
 
 APPLICATION_TAGS = ["Liquid Staking", "Dexes", "Yield", "Lending", "Yield Aggregator"]
 
@@ -2284,7 +2284,7 @@
         name="curve-daily-volume-fees",
         path="gs://datasets-giza/Curve/curve_daily_volume_fees.parquet",
         description="Daily Curve trade volume and fees generated in USD, per pool",
-        tags=["Curve","Trade Volume","Fees" ,"daily", "DeFi", "DEX"],
+        tags=["Curve", "Trade Volume", "Fees", "daily", "DeFi", "DEX"],
         documentation="https://datasets.gizatech.xyz/hub/curve/daily-trade-volume-and-fees",
     ),
     Dataset(
@@ -2302,4 +2302,3 @@
         documentation="",
     ),
 ]
-

giza_datasets/hub.py → giza/datasets/hub.py

@@ -1,7 +1,7 @@
 from rich.console import Console
 from rich.table import Table
 
-from giza_datasets.constants import DATASET_HUB
+from giza.datasets.constants import DATASET_HUB
 
 
 class DatasetsHub:

giza_datasets/loaders.py → giza/datasets/loaders.py

@@ -1,8 +1,10 @@
+import os
+
 import gcsfs
 import polars as pl
-import os
-from giza_datasets.constants import DATASET_HUB
-from giza_datasets.cache_manager import CacheManager
+
+from giza.datasets.cache_manager import CacheManager
+from giza.datasets.constants import DATASET_HUB
 
 
 class DatasetsLoader:
@@ -18,7 +20,7 @@ def __init__(self, use_cache=True, cache_dir=None):
         self.cache_dir = (
             cache_dir
             if cache_dir is not None
-            else os.path.join(os.path.expanduser("~"), ".cache/giza_datasets")
+            else os.path.join(os.path.expanduser("~"), ".cache/giza.datasets")
         )
         self.cache_manager = CacheManager(self.cache_dir) if use_cache else None
 

giza_datasets/models.py → giza/datasets/models.py

@@ -2,9 +2,9 @@
 
 from pydantic import BaseModel
 
-from giza_datasets.defillama_constants import DEFILLAMA_SUPPORTED_PROJECTS
+from giza.datasets.defillama_constants import DEFILLAMA_SUPPORTED_PROJECTS
 
-sector_tags = ["DeFi","Social"]
+sector_tags = ["DeFi", "Social"]
 application_tags = ["Liquid Staking", "DEX", "Yield", "Lending", "Yield Aggregator"]
 protocol_tags = DEFILLAMA_SUPPORTED_PROJECTS + [
     "Aave-v2",

pyproject.toml

@@ -5,8 +5,7 @@ description = ""
 authors = ["Fran Algaba <f.algaba@outlook.es>"]
 readme = "README.md"
 license = "MIT"
-include = ["datasets/*"]
-
+packages = [{include = "giza"}]
 
 [tool.poetry.dependencies]
 python = "^3.11"

tests/test_main.py

@@ -1,7 +1,7 @@
 import polars as pl
 import pytest
 
-from giza_datasets import DatasetsLoader
+from giza.datasets import DatasetsLoader
 
 
 def test_load_dataset_eager():