This is an automated email from the ASF dual-hosted git repository.
agrove pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/datafusion-python.git
The following commit(s) were added to refs/heads/main by this push:
new 57eb959 chore: fix typos (#844)
57eb959 is described below
commit 57eb9596e0a3d6205bd3e94e83854111145572e6
Author: Daniel Mesejo <[email protected]>
AuthorDate: Mon Sep 2 16:51:52 2024 +0200
chore: fix typos (#844)
- run [codespell](https://github.com/codespell-project/codespell) on the
source code
- change name of parameter in db-benchmark.dockerfile based on spelling
suggestion and
the documentation:
https://www.rdocumentation.org/packages/utils/versions/3.6.2/topics/install.packages
---
benchmarks/db-benchmark/db-benchmark.dockerfile | 2 +-
docs/mdbook/src/index.md | 2 +-
docs/source/_static/theme_overrides.css | 2 +-
docs/source/conf.py | 2 +-
docs/source/user-guide/common-operations/expressions.rst | 2 +-
examples/export.py | 2 +-
examples/python-udf-comparisons.py | 2 +-
examples/tpch/q02_minimum_cost_supplier.py | 2 +-
examples/tpch/q04_order_priority_checking.py | 4 ++--
examples/tpch/q06_forecasting_revenue_change.py | 2 +-
examples/tpch/q07_volume_shipping.py | 2 +-
examples/tpch/q11_important_stock_identification.py | 2 +-
examples/tpch/q15_top_supplier.py | 2 +-
examples/tpch/q20_potential_part_promotion.py | 2 +-
examples/tpch/q21_suppliers_kept_orders_waiting.py | 2 +-
examples/tpch/q22_global_sales_opportunity.py | 4 ++--
python/datafusion/context.py | 4 ++--
python/datafusion/expr.py | 2 +-
python/datafusion/functions.py | 10 +++++-----
python/datafusion/input/location.py | 4 ++--
python/datafusion/udf.py | 4 ++--
src/common/data_type.rs | 2 +-
src/expr/table_scan.rs | 2 +-
23 files changed, 32 insertions(+), 32 deletions(-)
diff --git a/benchmarks/db-benchmark/db-benchmark.dockerfile
b/benchmarks/db-benchmark/db-benchmark.dockerfile
index d8842b2..af2edd0 100644
--- a/benchmarks/db-benchmark/db-benchmark.dockerfile
+++ b/benchmarks/db-benchmark/db-benchmark.dockerfile
@@ -58,7 +58,7 @@ RUN cd pandas && \
RUN cd modin && \
virtualenv py-modin --python=/usr/bin/python3.10
-RUN Rscript -e 'install.packages(c("jsonlite","bit64","devtools","rmarkdown"),
dependecies=TRUE, repos="https://cloud.r-project.org";)'
+RUN Rscript -e 'install.packages(c("jsonlite","bit64","devtools","rmarkdown"),
dependencies=TRUE, repos="https://cloud.r-project.org";)'
SHELL ["/bin/bash", "-c"]
diff --git a/docs/mdbook/src/index.md b/docs/mdbook/src/index.md
index 3cd0fec..2c1d217 100644
--- a/docs/mdbook/src/index.md
+++ b/docs/mdbook/src/index.md
@@ -18,7 +18,7 @@
DataFusion is a blazing fast query engine that lets you run data analyses
quickly and reliably.
-DataFusion is written in Rust, but also exposes Python and SQL bindings, so
you can easily query data in your langauge of choice. You don't need to know
any Rust to be a happy and productive user of DataFusion.
+DataFusion is written in Rust, but also exposes Python and SQL bindings, so
you can easily query data in your language of choice. You don't need to know
any Rust to be a happy and productive user of DataFusion.
DataFusion lets you run queries faster than pandas. Let's compare query
runtimes for a 5GB CSV file with 100 million rows of data.
diff --git a/docs/source/_static/theme_overrides.css
b/docs/source/_static/theme_overrides.css
index 1e972cc..aaa40fb 100644
--- a/docs/source/_static/theme_overrides.css
+++ b/docs/source/_static/theme_overrides.css
@@ -56,7 +56,7 @@ a.navbar-brand img {
/* This is the bootstrap CSS style for "table-striped". Since the theme does
-not yet provide an easy way to configure this globaly, it easier to simply
+not yet provide an easy way to configure this globally, it easier to simply
include this snippet here than updating each table in all rst files to
add ":class: table-striped" */
diff --git a/docs/source/conf.py b/docs/source/conf.py
index d508455..2e5a413 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -15,7 +15,7 @@
# specific language governing permissions and limitations
# under the License.
-"""Documenation generation."""
+"""Documentation generation."""
# Configuration file for the Sphinx documentation builder.
#
diff --git a/docs/source/user-guide/common-operations/expressions.rst
b/docs/source/user-guide/common-operations/expressions.rst
index c8f8b8f..e35234c 100644
--- a/docs/source/user-guide/common-operations/expressions.rst
+++ b/docs/source/user-guide/common-operations/expressions.rst
@@ -21,7 +21,7 @@ Expressions
===========
In DataFusion an expression is an abstraction that represents a computation.
-Expressions are used as the primary inputs and ouputs for most functions within
+Expressions are used as the primary inputs and outputs for most functions
within
DataFusion. As such, expressions can be combined to create expression trees, a
concept shared across most compilers and databases.
diff --git a/examples/export.py b/examples/export.py
index d179bf3..cc02de5 100644
--- a/examples/export.py
+++ b/examples/export.py
@@ -48,6 +48,6 @@ assert polars_df.shape == (3, 2)
pylist = df.to_pylist()
assert pylist == [{"a": 1, "b": 4}, {"a": 2, "b": 5}, {"a": 3, "b": 6}]
-# export to Pyton dictionary of columns
+# export to Python dictionary of columns
pydict = df.to_pydict()
assert pydict == {"a": [1, 2, 3], "b": [4, 5, 6]}
diff --git a/examples/python-udf-comparisons.py
b/examples/python-udf-comparisons.py
index 5a6f548..9a84dd7 100644
--- a/examples/python-udf-comparisons.py
+++ b/examples/python-udf-comparisons.py
@@ -28,7 +28,7 @@ filepath = os.path.join(path, "./tpch/data/lineitem.parquet")
# question "return all of the rows that have a specific combination of these
# values". We have the combinations we care about provided as a python
# list of tuples. There is no built in function that supports this operation,
-# but it can be explicilty specified via a single expression or we can
+# but it can be explicitly specified via a single expression or we can
# use a user defined function.
ctx = SessionContext()
diff --git a/examples/tpch/q02_minimum_cost_supplier.py
b/examples/tpch/q02_minimum_cost_supplier.py
index f4020d7..2171a20 100644
--- a/examples/tpch/q02_minimum_cost_supplier.py
+++ b/examples/tpch/q02_minimum_cost_supplier.py
@@ -96,7 +96,7 @@ df = df_partsupp.join(df_supplier, (["ps_suppkey"],
["s_suppkey"]), how="inner")
# create a column of that value. We can then filter down any rows for which
the cost and
# minimum do not match.
-# The default window frame as of 5/6/2024 is from unbounded preceeding to the
current row.
+# The default window frame as of 5/6/2024 is from unbounded preceding to the
current row.
# We want to evaluate the entire data frame, so we specify this.
window_frame = datafusion.WindowFrame("rows", None, None)
df = df.with_column(
diff --git a/examples/tpch/q04_order_priority_checking.py
b/examples/tpch/q04_order_priority_checking.py
index 9dbd816..77c3bd4 100644
--- a/examples/tpch/q04_order_priority_checking.py
+++ b/examples/tpch/q04_order_priority_checking.py
@@ -53,9 +53,9 @@ interval = pa.scalar((0, INTERVAL_DAYS, 0),
type=pa.month_day_nano_interval())
# Limit results to cases where commitment date before receipt date
# Aggregate the results so we only get one row to join with the order table.
-# Alterately, and likely more idomatic is instead of `.aggregate` you could
+# Alternately, and likely more idiomatic is instead of `.aggregate` you could
# do `.select_columns("l_orderkey").distinct()`. The goal here is to show
-# mulitple examples of how to use Data Fusion.
+# multiple examples of how to use Data Fusion.
df_lineitem = df_lineitem.filter(col("l_commitdate") <
col("l_receiptdate")).aggregate(
[col("l_orderkey")], []
)
diff --git a/examples/tpch/q06_forecasting_revenue_change.py
b/examples/tpch/q06_forecasting_revenue_change.py
index ec98aaf..3beb9eb 100644
--- a/examples/tpch/q06_forecasting_revenue_change.py
+++ b/examples/tpch/q06_forecasting_revenue_change.py
@@ -82,5 +82,5 @@ df = df.aggregate(
revenue = df.collect()[0]["revenue"][0].as_py()
-# Note: the output value from this query may be dependant on the size of the
database generated
+# Note: the output value from this query may be dependent on the size of the
database generated
print(f"Potential lost revenue: {revenue:.2f}")
diff --git a/examples/tpch/q07_volume_shipping.py
b/examples/tpch/q07_volume_shipping.py
index fd7323b..44c605a 100644
--- a/examples/tpch/q07_volume_shipping.py
+++ b/examples/tpch/q07_volume_shipping.py
@@ -77,7 +77,7 @@ df_lineitem = df_lineitem.filter(col("l_shipdate") >=
start_date).filter(
# the two nations of interest. Since there is no `otherwise()` statement, any
values that do
# not match these will result in a null value and then get filtered out.
#
-# To do the same using a simle filter would be:
+# To do the same using a simple filter would be:
# df_nation = df_nation.filter((F.col("n_name") == nation_1) |
(F.col("n_name") == nation_2))
df_nation = df_nation.with_column(
"n_name",
diff --git a/examples/tpch/q11_important_stock_identification.py
b/examples/tpch/q11_important_stock_identification.py
index 2672487..391eb45 100644
--- a/examples/tpch/q11_important_stock_identification.py
+++ b/examples/tpch/q11_important_stock_identification.py
@@ -63,7 +63,7 @@ df = df.with_column("value", col("ps_supplycost") *
col("ps_availqty"))
# Compute total value of specific parts
df = df.aggregate([col("ps_partkey")], [F.sum(col("value")).alias("value")])
-# By default window functions go from unbounded preceeding to current row, but
we want
+# By default window functions go from unbounded preceding to current row, but
we want
# to compute this sum across all rows
window_frame = WindowFrame("rows", None, None)
diff --git a/examples/tpch/q15_top_supplier.py
b/examples/tpch/q15_top_supplier.py
index 4b9e4c1..aa76093 100644
--- a/examples/tpch/q15_top_supplier.py
+++ b/examples/tpch/q15_top_supplier.py
@@ -78,7 +78,7 @@ df = df.filter(col("total_revenue") == col("max_revenue"))
# from the supplier table
df = df.join(df_supplier, (["l_suppkey"], ["s_suppkey"]), "inner")
-# Return only the colums requested
+# Return only the columns requested
df = df.select_columns("s_suppkey", "s_name", "s_address", "s_phone",
"total_revenue")
# If we have more than one, sort by supplier number (suppkey)
diff --git a/examples/tpch/q20_potential_part_promotion.py
b/examples/tpch/q20_potential_part_promotion.py
index 05a2674..4ced7aa 100644
--- a/examples/tpch/q20_potential_part_promotion.py
+++ b/examples/tpch/q20_potential_part_promotion.py
@@ -74,7 +74,7 @@ df = df_lineitem.filter(col("l_shipdate") >=
lit(date)).filter(
# This will filter down the line items to the parts of interest
df = df.join(df_part, (["l_partkey"], ["p_partkey"]), "inner")
-# Compute the total sold and limit ourselves to indivdual supplier/part
combinations
+# Compute the total sold and limit ourselves to individual supplier/part
combinations
df = df.aggregate(
[col("l_partkey"), col("l_suppkey")],
[F.sum(col("l_quantity")).alias("total_sold")]
)
diff --git a/examples/tpch/q21_suppliers_kept_orders_waiting.py
b/examples/tpch/q21_suppliers_kept_orders_waiting.py
index 9f59804..6b1679e 100644
--- a/examples/tpch/q21_suppliers_kept_orders_waiting.py
+++ b/examples/tpch/q21_suppliers_kept_orders_waiting.py
@@ -74,7 +74,7 @@ df = df.with_column(
# only orders where this array is larger than one for multiple supplier
orders. The second column
# is all of the suppliers who failed to make their commitment. We can filter
the second column for
# arrays with size one. That combination will give us orders that had multiple
suppliers where only
-# one failed. Use distinct=True in the blow aggregation so we don't get
multipe line items from the
+# one failed. Use distinct=True in the blow aggregation so we don't get
multiple line items from the
# same supplier reported in either array.
df = df.aggregate(
[col("o_orderkey")],
diff --git a/examples/tpch/q22_global_sales_opportunity.py
b/examples/tpch/q22_global_sales_opportunity.py
index 622c142..41fd5de 100644
--- a/examples/tpch/q22_global_sales_opportunity.py
+++ b/examples/tpch/q22_global_sales_opportunity.py
@@ -45,14 +45,14 @@ df_orders =
ctx.read_parquet(get_data_path("orders.parquet")).select_columns(
# The nation code is a two digit number, but we need to convert it to a string
literal
nation_codes = F.make_array(*[lit(str(n)) for n in NATION_CODES])
-# Use the substring operation to extract the first two charaters of the phone
number
+# Use the substring operation to extract the first two characters of the phone
number
df = df_customer.with_column("cntrycode", F.substring(col("c_phone"), lit(0),
lit(3)))
# Limit our search to customers with some balance and in the country code above
df = df.filter(col("c_acctbal") > lit(0.0))
df = df.filter(~F.array_position(nation_codes, col("cntrycode")).is_null())
-# Compute the average balance. By default, the window frame is from unbounded
preceeding to the
+# Compute the average balance. By default, the window frame is from unbounded
preceding to the
# current row. We want our frame to cover the entire data frame.
window_frame = WindowFrame("rows", None, None)
df = df.with_column(
diff --git a/python/datafusion/context.py b/python/datafusion/context.py
index 283f71e..f6bf1c6 100644
--- a/python/datafusion/context.py
+++ b/python/datafusion/context.py
@@ -436,7 +436,7 @@ class SessionContext:
Example usage:
- The following example demostrates how to use the context to execute
+ The following example demonstrates how to use the context to execute
a query against a CSV data source using the :py:class:`DataFrame` API::
from datafusion import SessionContext
@@ -853,7 +853,7 @@ class SessionContext:
return DataFrame(self.ctx.empty_table())
def session_id(self) -> str:
- """Retrun an id that uniquely identifies this
:py:class:`SessionContext`."""
+ """Return an id that uniquely identifies this
:py:class:`SessionContext`."""
return self.ctx.session_id()
def read_json(
diff --git a/python/datafusion/expr.py b/python/datafusion/expr.py
index c7272bb..742f8e4 100644
--- a/python/datafusion/expr.py
+++ b/python/datafusion/expr.py
@@ -515,7 +515,7 @@ class WindowFrame:
Args:
units: Should be one of ``rows``, ``range``, or ``groups``.
- start_bound: Sets the preceeding bound. Must be >= 0. If none, this
+ start_bound: Sets the preceding bound. Must be >= 0. If none, this
will be set to unbounded. If unit type is ``groups``, this
parameter must be set.
end_bound: Sets the following bound. Must be >= 0. If none, this
diff --git a/python/datafusion/functions.py b/python/datafusion/functions.py
index 28201c1..120fed8 100644
--- a/python/datafusion/functions.py
+++ b/python/datafusion/functions.py
@@ -342,7 +342,7 @@ def concat(*args: Expr) -> Expr:
def concat_ws(separator: str, *args: Expr) -> Expr:
"""Concatenates the list ``args`` with the separator.
- ``NULL`` arugments are ignored. ``separator`` should not be ``NULL``.
+ ``NULL`` arguments are ignored. ``separator`` should not be ``NULL``.
"""
args = [arg.expr for arg in args]
return Expr(f.concat_ws(separator, args))
@@ -541,7 +541,7 @@ def ends_with(arg: Expr, suffix: Expr) -> Expr:
def exp(arg: Expr) -> Expr:
- """Returns the exponential of the arugment."""
+ """Returns the exponential of the argument."""
return Expr(f.exp(arg.expr))
@@ -1593,7 +1593,7 @@ def grouping(arg: Expr, distinct: bool = False) -> Expr:
def max(arg: Expr, distinct: bool = False) -> Expr:
- """Returns the maximum value of the arugment."""
+ """Returns the maximum value of the argument."""
return Expr(f.max(arg.expr, distinct=distinct))
@@ -1769,12 +1769,12 @@ def bit_xor(arg: Expr, distinct: bool = False) -> Expr:
def bool_and(arg: Expr, distinct: bool = False) -> Expr:
- """Computes the boolean AND of the arugment."""
+ """Computes the boolean AND of the argument."""
return Expr(f.bool_and(arg.expr, distinct=distinct))
def bool_or(arg: Expr, distinct: bool = False) -> Expr:
- """Computes the boolean OR of the arguement."""
+ """Computes the boolean OR of the argument."""
return Expr(f.bool_or(arg.expr, distinct=distinct))
diff --git a/python/datafusion/input/location.py
b/python/datafusion/input/location.py
index 566a63d..b274539 100644
--- a/python/datafusion/input/location.py
+++ b/python/datafusion/input/location.py
@@ -66,7 +66,7 @@ class LocationInputPlugin(BaseInputSource):
# Consume header row and count number of rows for statistics.
# TODO: Possibly makes sense to have the eager number of rows
# calculated as a configuration since you must read the entire file
- # to get that information. However, this should only be occuring
+ # to get that information. However, this should only be occurring
# at table creation time and therefore shouldn't
# slow down query performance.
with open(input_file, "r") as file:
@@ -75,7 +75,7 @@ class LocationInputPlugin(BaseInputSource):
print(header_row)
for _ in reader:
num_rows += 1
- # TODO: Need to actually consume this row into resonable columns
+ # TODO: Need to actually consume this row into reasonable columns
raise RuntimeError("TODO: Currently unable to support CSV input
files.")
else:
raise RuntimeError(
diff --git a/python/datafusion/udf.py b/python/datafusion/udf.py
index bdbad66..a3b74bb 100644
--- a/python/datafusion/udf.py
+++ b/python/datafusion/udf.py
@@ -153,7 +153,7 @@ class Accumulator(metaclass=ABCMeta):
@abstractmethod
def update(self, values: pyarrow.Array) -> None:
- """Evalute an array of values and update state."""
+ """Evaluate an array of values and update state."""
pass
@abstractmethod
@@ -189,7 +189,7 @@ class AggregateUDF:
) -> None:
"""Instantiate a user defined aggregate function (UDAF).
- See :py:func:`udaf` for a convenience function and arugment
+ See :py:func:`udaf` for a convenience function and argument
descriptions.
"""
self._udf = df_internal.AggregateUDF(
diff --git a/src/common/data_type.rs b/src/common/data_type.rs
index 21b085c..bdfc5a6 100644
--- a/src/common/data_type.rs
+++ b/src/common/data_type.rs
@@ -40,7 +40,7 @@ pub enum RexType {
/// Arrow types which represents the underlying arrow format
/// Python types which represent the type in Python
/// It is important to keep all of those types in a single
-/// and managable location. Therefore this structure exists
+/// and manageable location. Therefore this structure exists
/// to map those types and provide a simple place for developers
/// to map types from one system to another.
#[derive(Debug, Clone)]
diff --git a/src/expr/table_scan.rs b/src/expr/table_scan.rs
index 8fafd12..386c43b 100644
--- a/src/expr/table_scan.rs
+++ b/src/expr/table_scan.rs
@@ -94,7 +94,7 @@ impl PyTableScan {
/// The column indexes that should be. Note if this is empty then
/// all columns should be read by the `TableProvider`. This function
- /// provides a Tuple of the (index, column_name) to make things simplier
+ /// provides a Tuple of the (index, column_name) to make things simpler
/// for the calling code since often times the name is preferred to
/// the index which is a lower level abstraction.
#[pyo3(name = "projection")]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
