[arrow-datafusion] branch master updated: python: update user doc to use new APIs (#1287)

[houqp]

This is an automated email from the ASF dual-hosted git repository.

houqp pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow-datafusion.git


The following commit(s) were added to refs/heads/master by this push:
     new b773802  python: update user doc to use new APIs (#1287)
b773802 is described below

commit b77380250d7f779a5f7e24fb6f54d638692bf1de
Author: QP Hou <q...@scribd.com>
AuthorDate: Sat Nov 13 13:18:33 2021 -0800

    python: update user doc to use new APIs (#1287)
    
    also implement __str__ for PyExpr and updated docs
---
 .github/workflows/python_test.yaml |  2 +-
 docs/source/python/index.rst       | 13 ++++++-------
 python/datafusion/__init__.py      |  7 +++++++
 python/src/expression.rs           |  4 ++++
 4 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/.github/workflows/python_test.yaml 
b/.github/workflows/python_test.yaml
index 905b9c5..01a36af 100644
--- a/.github/workflows/python_test.yaml
+++ b/.github/workflows/python_test.yaml
@@ -50,7 +50,7 @@ jobs:
         run: |
           source venv/bin/activate
           flake8 python --ignore=E501
-          black --line-length 79 --check python
+          black --line-length 79 --diff --check python
       - name: Run tests
         run: |
           source venv/bin/activate
diff --git a/docs/source/python/index.rst b/docs/source/python/index.rst
index 56f9097..57ab8d1 100644
--- a/docs/source/python/index.rst
+++ b/docs/source/python/index.rst
@@ -39,11 +39,10 @@ Simple usage:
 .. code-block:: python
 
    import datafusion
+   from datafusion import functions as f
+   from datafusion import col
    import pyarrow
 
-   # an alias
-   f = datafusion.functions
-
    # create a context
    ctx = datafusion.ExecutionContext()
 
@@ -56,8 +55,8 @@ Simple usage:
 
    # create a new statement
    df = df.select(
-       f.col("a") + f.col("b"),
-       f.col("a") - f.col("b"),
+       col("a") + col("b"),
+       col("a") - col("b"),
    )
 
    # execute and collect the first (and only) batch
@@ -77,7 +76,7 @@ UDFs
 
    udf = f.udf(is_null, [pyarrow.int64()], pyarrow.bool_())
 
-   df = df.select(udf(f.col("a")))
+   df = df.select(udf(col("a")))
 
 
 UDAF
@@ -117,7 +116,7 @@ UDAF
 
    df = df.aggregate(
        [],
-       [udaf(f.col("a"))]
+       [udaf(col("a"))]
    )
 
 
diff --git a/python/datafusion/__init__.py b/python/datafusion/__init__.py
index 4f9082e..0a25592 100644
--- a/python/datafusion/__init__.py
+++ b/python/datafusion/__init__.py
@@ -28,6 +28,7 @@ from ._internal import (
     ScalarUDF,
 )
 
+
 __all__ = [
     "DataFrame",
     "ExecutionContext",
@@ -61,12 +62,18 @@ def column(value):
     return Expression.column(value)
 
 
+col = column
+
+
 def literal(value):
     if not isinstance(value, pa.Scalar):
         value = pa.scalar(value)
     return Expression.literal(value)
 
 
+lit = literal
+
+
 def udf(func, input_types, return_type, volatility, name=None):
     """
     Create a new User Defined Function
diff --git a/python/src/expression.rs b/python/src/expression.rs
index 21cecaa..5e1cad2 100644
--- a/python/src/expression.rs
+++ b/python/src/expression.rs
@@ -90,6 +90,10 @@ impl PyObjectProtocol for PyExpr {
         };
         expr.into()
     }
+
+    fn __str__(&self) -> PyResult<String> {
+        Ok(format!("{}", self.expr))
+    }
 }
 
 #[pymethods]