rename

.gitignore

@@ -171,3 +171,6 @@ cython_debug/
 .pypirc
 
 local/
+
+docs/site/
+site/

README.md

@@ -1 +1 @@
-# pandas_lazy
+# lazy_pandas

docs/docs/index.md

@@ -1,35 +1,35 @@
 ---
-title: Pandas Lazy
+title: Lazy Pandas
 hide:
   - navigation
   - toc
 ---
 
-# Pandas Lazy
+# Lazy Pandas
 
-Welcome to the **Pandas Lazy** official documentation!
+Welcome to the **Lazy Pandas** official documentation!
 A library inspired by [pandas](https://pandas.pydata.org/) that focuses on *lazy* processing, enabling high performance and lower memory usage for large datasets.
 
-## What is Pandas Lazy?
+## What is Lazy Pandas?
 
-Pandas Lazy is built on the concept of delaying DataFrame operations until they are strictly necessary (lazy evaluation). This allows:
+Lazy Pandas is built on the concept of delaying DataFrame operations until they are strictly necessary (lazy evaluation). This allows:
 - Operations to be optimized in batches.
 - Memory usage to be minimized during processing.
 - Total runtime to be reduced for complex pipelines.
 
 ## Code Comparison
 
-Below is a side-by-side comparison showing how the same operation would look in **pandas** versus **Pandas Lazy**:
+Below is a side-by-side comparison showing how the same operation would look in **Pandas** versus **Lazy Pandas**:
 
 
-=== "Pandas Lazy"
+=== "Lazy Pandas"
 
     ```python linenums="1" hl_lines="2 5 13"
     import pandas as pd
-    import pandas_lazy as pdl
+    import lazy_pandas as lpd
 
     def read_taxi_dataset(location: str) -> pd.DataFrame:
-        df = pdl.read_csv(location, parse_dates=["pickup_datetime"])
+        df = lpd.read_csv(location, parse_dates=["pickup_datetime"])
         df = df[["pickup_datetime", "passenger_count"]]
         df["passenger_count"] = df["passenger_count"]
         df["pickup_date"] = df["pickup_datetime"].dt.date
@@ -61,11 +61,11 @@ Below is a side-by-side comparison showing how the same operation would look in
         return df
     ```
 
-Notice that in traditional **pandas**, operations are executed immediately, while in **Pandas Lazy**, computation only occurs when you call `.collect()`.
+Notice that in traditional **pandas**, operations are executed immediately, while in **Lazy Pandas**, computation only occurs when you call `.collect()`.
 
 ## Memory Usage
 
-Below is a fictitious performance comparison between **pandas** and **Pandas Lazy**, showing a scenario where a large dataset is processed in three stages (reading, aggregation, and complex filtering).
+Below is a fictitious performance comparison between **pandas** and **Lazy Pandas**, showing a scenario where a large dataset is processed in three stages (reading, aggregation, and complex filtering).
 
 
 <div class="grid cards" markdown>

docs/mkdocs.yml

@@ -1,8 +1,9 @@
-site_name: PandasLazy
-repo_url: https://github.com/mariotaddeucci/pandas-lazy
-repo_name: mariotaddeucci/pandas-lazy
+site_name: LazyPandas
+repo_url: https://github.com/mariotaddeucci/lazy-pandas
+repo_name: mariotaddeucci/lazy-pandas
 theme:
   name: material
+  logo: assets/logo.png
   palette:
     - media: "(prefers-color-scheme: light)"
       scheme: default

docs/scripts/generate_references.py

@@ -4,36 +4,33 @@
 import mkdocs_gen_files
 
 package_dir = Path(__file__).parent.parent.parent / "src"
-
-print(str(package_dir))
 sys.path.insert(0, str(package_dir))
 
-
-import pandas_lazy as pdl  # noqa: E402
+import lazy_pandas as lpd  # noqa: E402
 
 vls = []
 
 vls += [
-    (1000 + idx, "pandas_lazy.LazyFrame", f"LazyFrame.{attr}", attr)
-    for idx, attr in enumerate(sorted(dir(pdl.LazyFrame)))
+    (1000 + idx, "lazy_pandas.LazyFrame", f"LazyFrame.{attr}", attr)
+    for idx, attr in enumerate(sorted(dir(lpd.LazyFrame)))
     if not attr.startswith("_")
 ]
 
 vls += [
-    (1000 + idx, "pandas_lazy.LazyColumn", f"LazyColumn.{attr}", attr)
-    for idx, attr in enumerate(sorted(dir(pdl.LazyColumn)))
+    (1000 + idx, "lazy_pandas.LazyColumn", f"LazyColumn.{attr}", attr)
+    for idx, attr in enumerate(sorted(dir(lpd.LazyColumn)))
     if not attr.startswith("_") and attr not in ["str", "dt", "create_from_function"]
 ]
 
 vls += [
-    (2000 + idx, "pandas_lazy.LazyStringColumn", f"LazyColumn.str.{attr}", attr)
-    for idx, attr in enumerate(sorted(dir(pdl.LazyStringColumn)))
+    (2000 + idx, "lazy_pandas.LazyStringColumn", f"LazyColumn.str.{attr}", attr)
+    for idx, attr in enumerate(sorted(dir(lpd.LazyStringColumn)))
     if not attr.startswith("_")
 ]
 
 vls += [
-    (3000 + idx, "pandas_lazy.LazyDateTimeColumn", f"LazyColumn.dt.{attr}", attr)
-    for idx, attr in enumerate(sorted(dir(pdl.LazyDateTimeColumn)))
+    (3000 + idx, "lazy_pandas.LazyDateTimeColumn", f"LazyColumn.dt.{attr}", attr)
+    for idx, attr in enumerate(sorted(dir(lpd.LazyDateTimeColumn)))
     if not attr.startswith("_")
 ]
 
@@ -53,21 +50,21 @@
 
 fn_names = [
     attr
-    for idx, attr in enumerate(sorted(dir(pdl)))
+    for idx, attr in enumerate(sorted(dir(lpd)))
     if not attr.startswith("_")
-    and callable(getattr(pdl, attr))
+    and callable(getattr(lpd, attr))
     and attr not in ["LazyFrame", "LazyColumn", "LazyStringColumn", "LazyDateTimeColumn"]
 ]
 
 
 template = """
-# pdl.{function_name}
-::: pandas_lazy.{function_name}
+# lpd.{function_name}
+::: lazy_pandas.{function_name}
     options:
         members:
         - {function_name}
 """
 
 for function_name in fn_names:
-    with mkdocs_gen_files.open(f"references/General_Functions/pandas_lazy{function_name}.md", "w") as f:
+    with mkdocs_gen_files.open(f"references/General_Functions/lazy_pandas{function_name}.md", "w") as f:
         f.write(template.format(function_name=function_name))

pyproject.toml

@@ -13,7 +13,7 @@ description = "Add your description here"
 dynamic = [
     "version",
 ]
-name = "pandas_lazy"
+name = "lazy_pandas"
 readme = "README.md"
 requires-python = ">=3.10"
 

src/lazy_pandas/__init__.py

@@ -0,0 +1,17 @@
+from lazy_pandas.column.lazy_column import LazyColumn
+from lazy_pandas.column.lazy_datetime_column import LazyDateTimeColumn
+from lazy_pandas.column.lazy_string_column import LazyStringColumn
+from lazy_pandas.frame.lazy_frame import LazyFrame
+from lazy_pandas.general import from_pandas, read_csv, read_delta, read_iceberg, read_parquet
+
+__all__ = [
+    "LazyFrame",
+    "LazyColumn",
+    "read_csv",
+    "read_parquet",
+    "from_pandas",
+    "read_delta",
+    "read_iceberg",
+    "LazyDateTimeColumn",
+    "LazyStringColumn",
+]

src/pandas_lazy/column/lazy_column.py → src/lazy_pandas/column/lazy_column.py

@@ -3,8 +3,8 @@
 from duckdb import CoalesceOperator, ConstantExpression, Expression, FunctionExpression
 from duckdb.typing import DuckDBPyType
 
-from pandas_lazy.column.lazy_datetime_column import LazyDateTimeColumn
-from pandas_lazy.column.lazy_string_column import LazyStringColumn
+from lazy_pandas.column.lazy_datetime_column import LazyDateTimeColumn
+from lazy_pandas.column.lazy_string_column import LazyStringColumn
 
 __all__ = ["LazyColumn"]
 

src/pandas_lazy/column/lazy_datetime_column.py → src/lazy_pandas/column/lazy_datetime_column.py

@@ -3,7 +3,7 @@
 from duckdb import ConstantExpression
 
 if TYPE_CHECKING:
-    from pandas_lazy.column.lazy_column import LazyColumn
+    from lazy_pandas.column.lazy_column import LazyColumn
 
 
 class LazyDateTimeColumn:

src/pandas_lazy/column/lazy_string_column.py → src/lazy_pandas/column/lazy_string_column.py

@@ -3,7 +3,7 @@
 from duckdb import ConstantExpression
 
 if TYPE_CHECKING:
-    from pandas_lazy.column.lazy_column import LazyColumn
+    from lazy_pandas.column.lazy_column import LazyColumn
 
 
 class LazyStringColumn:

src/lazy_pandas/exceptions.py

@@ -0,0 +1 @@
+class LazyPandasUnsupporttedOperation(Exception): ...

src/pandas_lazy/frame/lazy_frame.py → src/lazy_pandas/frame/lazy_frame.py

@@ -12,9 +12,9 @@
 )
 from duckdb.typing import DuckDBPyType
 
-from pandas_lazy.column.lazy_column import LazyColumn
-from pandas_lazy.exceptions import PandasLazyUnsupporttedOperation
-from pandas_lazy.frame.lazy_groupped_frame import LazyGrouppedFrame
+from lazy_pandas.column.lazy_column import LazyColumn
+from lazy_pandas.exceptions import LazyPandasUnsupporttedOperation
+from lazy_pandas.frame.lazy_groupped_frame import LazyGrouppedFrame
 
 if TYPE_CHECKING:
     import pandas as pd
@@ -281,7 +281,7 @@ def __getitem__(self, key: str | list[str] | LazyColumn) -> Union[LazyColumn, "L
             LazyColumn or LazyFrame: The selected column or a LazyFrame with the selected columns.
 
         Raises:
-            PandasLazyUnsupporttedOperation: If an unsupported operation is attempted.
+            LazyPandasUnsupporttedOperation: If an unsupported operation is attempted.
         """
         if isinstance(key, list):
             return LazyFrame(self._relation.select(*key))
@@ -292,8 +292,8 @@ def __getitem__(self, key: str | list[str] | LazyColumn) -> Union[LazyColumn, "L
         if isinstance(key, LazyColumn):
             return LazyFrame(self._relation.filter(key.expr))
 
-        raise PandasLazyUnsupporttedOperation(
-            f"PandasLazy does not support all pandas operations, use collect() to get a pandas DataFrame and then perform the operation {key}"
+        raise LazyPandasUnsupporttedOperation(
+            f"LazyPandas does not support all pandas operations, use collect() to get a pandas DataFrame and then perform the operation {key}"
         )
 
     def __setitem__(self, key, value) -> None:

src/pandas_lazy/frame/lazy_groupped_frame.py → src/lazy_pandas/frame/lazy_groupped_frame.py

@@ -3,7 +3,7 @@
 from duckdb import DuckDBPyRelation
 
 if TYPE_CHECKING:
-    from pandas_lazy import LazyFrame
+    from lazy_pandas import LazyFrame
 
 
 class LazyGrouppedFrame:

src/pandas_lazy/general.py → src/lazy_pandas/general.py

@@ -2,8 +2,7 @@
 
 import duckdb
 import duckdb.typing
-
-from pandas_lazy.frame.lazy_frame import LazyFrame
+from lazy_pandas.frame.lazy_frame import LazyFrame
 
 
 def from_pandas(df) -> LazyFrame:
@@ -19,9 +18,9 @@ def from_pandas(df) -> LazyFrame:
     Example:
     ```python
     import pandas as pd
-    import pandas_lazy as pdl
+    import lazy_pandas as lpd
     df = pd.DataFrame({'column1': [1, 2, 3], 'column2': ['a', 'b', 'c']})
-    lazy_df = pdl.from_pandas(df)
+    lazy_df = lpd.from_pandas(df)
     ```
     """
     return LazyFrame(duckdb.from_df(df))
@@ -116,8 +115,8 @@ def read_csv(
 
     Example:
     ```python
-    import pandas_lazy as pdl
-    df = pdl.read_csv('data.csv', header=True, sep=',', dtype={'column1': 'INTEGER', 'column2': 'VARCHAR'})
+    import lazy_pandas as lpd
+    df = lpd.read_csv('data.csv', header=True, sep=',', dtype={'column1': 'INTEGER', 'column2': 'VARCHAR'})
     df.head()
     ```
     """
@@ -219,8 +218,8 @@ def read_json(
 
     Example:
     ```python
-    import pandas_lazy as pdl
-    df = pdl.read_json('data.json', columns={'userId': 'INTEGER', 'completed': 'BOOLEAN'}, format='array')
+    import lazy_pandas as lpd
+    df = lpd.read_json('data.json', columns={'userId': 'INTEGER', 'completed': 'BOOLEAN'}, format='array')
     df.head()
     ```
     """
@@ -276,8 +275,8 @@ def read_parquet(
 
     Example:
     ```python
-    import pandas_lazy as pdl
-    df = pdl.read_parquet('data.parquet', columns=['column1', 'column2'])
+    import lazy_pandas as lpd
+    df = lpd.read_parquet('data.parquet', columns=['column1', 'column2'])
     df.head()
     ```
     """
@@ -307,9 +306,9 @@ def read_delta(path: str, *, conn: duckdb.DuckDBPyConnection | None = None) -> L
 
     Example:
     ```python
-    import pandas_lazy as pdl
+    import lazy_pandas as lpd
     from datetime import date
-    df = pdl.read_delta('s3://bucket/path_to_delta_table')
+    df = lpd.read_delta('s3://bucket/path_to_delta_table')
     df.head()
     ```
     """
@@ -332,8 +331,8 @@ def read_iceberg(path: str, *, conn: duckdb.DuckDBPyConnection | None = None) ->
 
     Example:
     ```python
-    import pandas_lazy as pdl
-    df = pdl.read_iceberg('s3://bucket/path_to_iceberg_table')
+    import lazy_pandas as lpd
+    df = lpd.read_iceberg('s3://bucket/path_to_iceberg_table')
     df.head()
     ```
     """