From 9827b83b5d5605ea39b4633c95bc0486a7822822 Mon Sep 17 00:00:00 2001 From: enstenr Date: Mon, 24 Nov 2025 09:58:39 +0000 Subject: [PATCH 1/4] Fixed broken link --- sql.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sql.ipynb b/sql.ipynb index 281e38b8..13c19086 100644 --- a/sql.ipynb +++ b/sql.ipynb @@ -79,7 +79,7 @@ "\n", "Input type can also be specified explicitly by providing a `format`.\n", "When being registered, tables can optionally be persisted into memory by passing `persist=True`, which can greatly speed up repeated queries on the same table at the cost of loading the entire table into memory.\n", - "For more information, see [Data Loading and Input](https://dask-sql.readthedocs.io/en/latest/pages/data_input.html)." + "For more information, see [Data Loading and Input](https://dask-sql.readthedocs.io/en/latest/data_input.html)." ] }, { @@ -473,7 +473,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.12" + "version": "3.12.3" } }, "nbformat": 4, From 1fc1f400959fa4d9320108a1aa53ff0ffb0fce62 Mon Sep 17 00:00:00 2001 From: enstenr Date: Mon, 24 Nov 2025 10:04:30 +0000 Subject: [PATCH 2/4] Fixed broken link --- dataframes/03-from-pandas-to-dask.ipynb | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/dataframes/03-from-pandas-to-dask.ipynb b/dataframes/03-from-pandas-to-dask.ipynb index 9333436e..b37060c9 100644 --- a/dataframes/03-from-pandas-to-dask.ipynb +++ b/dataframes/03-from-pandas-to-dask.ipynb @@ -992,7 +992,7 @@ "metadata": {}, "source": [ "We can do better... \n", - "Using [dask custom aggregation](https://docs.dask.org/en/latest/generated/dask.dataframe.groupby.Aggregation.html) is consideribly better" + "Using [dask custom aggregation](https://docs.dask.org/en/stable/generated/dask.dataframe.Aggregation.html) is consideribly better" ] }, { @@ -1206,7 +1206,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.12" + "version": "3.12.3" }, "mimetype": "text/x-python", "name": "python", From 589c5a4286787db77d87c55211ffacd86c32b200 Mon Sep 17 00:00:00 2001 From: enstenr Date: Mon, 24 Nov 2025 18:27:25 +0000 Subject: [PATCH 3/4] Added example for bag groupby and foldby as requested in issue 46 --- bag.ipynb | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/bag.ipynb b/bag.ipynb index 7def4ac6..b27ce93c 100644 --- a/bag.ipynb +++ b/bag.ipynb @@ -138,6 +138,26 @@ "b.count().compute() # Count total number of records" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "(b.groupby(lambda record:record[\"occupation\"]).map(lambda kv: ( kv[0], len(kv[1]))).compute()[:10]) # using groupby to count people in each occupation" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "city_counts = b.foldby(key = lambda record:record[\"address\"][\"city\"], binop = lambda acc, record:acc + 1, initial = 0 ) # using foldby to count people living by city\n", + "city_counts.take(10)" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -295,7 +315,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.12" + "version": "3.12.3" } }, "nbformat": 4, From acb99bfe5f5056f614a39d9c12affe053fe56da0 Mon Sep 17 00:00:00 2001 From: enstenr Date: Mon, 24 Nov 2025 18:29:08 +0000 Subject: [PATCH 4/4] Revert " Added example for bag groupby and foldby as requested in issue 46" This reverts commit 589c5a4286787db77d87c55211ffacd86c32b200. --- bag.ipynb | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) diff --git a/bag.ipynb b/bag.ipynb index b27ce93c..7def4ac6 100644 --- a/bag.ipynb +++ b/bag.ipynb @@ -138,26 +138,6 @@ "b.count().compute() # Count total number of records" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "\n", - "(b.groupby(lambda record:record[\"occupation\"]).map(lambda kv: ( kv[0], len(kv[1]))).compute()[:10]) # using groupby to count people in each occupation" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "city_counts = b.foldby(key = lambda record:record[\"address\"][\"city\"], binop = lambda acc, record:acc + 1, initial = 0 ) # using foldby to count people living by city\n", - "city_counts.take(10)" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -315,7 +295,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.12.3" + "version": "3.9.12" } }, "nbformat": 4,