Skip to content

updated methods and functions to polars 0.20.13 in ipynotebook #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

updated methods and functions to polars 0.20.13 in ipynotebook #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9f13dfb
updated methods and functions to polars 0.20.13
mattkeanny Mar 3, 2024
dabd4a1
updated cheat sheet and url links to polars 0.20.13
mattkeanny Mar 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 16 additions & 13 deletions polars-cheat-sheet.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,7 +118,7 @@
"metadata": {},
"outputs": [],
"source": [
"df.filter(pl.col(\"nrs\") < 4).groupby(\"groups\").agg(pl.all().sum())"
"df.filter(pl.col(\"nrs\") < 4).group_by(\"groups\").agg(pl.all().sum())"
]
},
{
Expand Down Expand Up @@ -150,7 +150,7 @@
"source": [
"# Sample\n",
"# Randomly select fraction of rows.\n",
"df.sample(frac=0.5)\n",
"df.sample(fraction=0.5)\n",
"\n",
"# Randomly select n rows.\n",
"df.sample(n=2)"
Expand Down Expand Up @@ -240,7 +240,10 @@
"outputs": [],
"source": [
"# Select rows meeting logical condition, and only the specific columns.\n",
"df[df[\"random\"] > 0.5, [\"names\", \"groups\"]]"
"(df\n",
" .filter(pl.col(\"random\") > 0.5)\n",
" .select(['names', 'groups'])\n",
")"
]
},
{
Expand Down Expand Up @@ -339,7 +342,7 @@
"outputs": [],
"source": [
"# Order rows by values of a column (high to low)\n",
"df.sort(\"random\", reverse=True)"
"df.sort(\"random\", descending=True)"
]
},
{
Expand Down Expand Up @@ -481,7 +484,7 @@
"outputs": [],
"source": [
"# Group by values in column named \"col\", returning a GroupBy object\n",
"df.groupby(\"groups\")"
"df.group_by(\"groups\")"
]
},
{
Expand All @@ -492,7 +495,7 @@
"outputs": [],
"source": [
"# All of the aggregation functions from above can be applied to a group as well\n",
"df.groupby(by=\"groups\").agg(\n",
"df.group_by(\"groups\").agg(\n",
" [\n",
" # Sum values\n",
" pl.sum(\"random\").alias(\"sum\"),\n",
Expand Down Expand Up @@ -528,12 +531,12 @@
"outputs": [],
"source": [
"# Additional GroupBy functions\n",
"df.groupby(by=\"groups\").agg(\n",
"df.group_by(\"groups\").agg(\n",
" [\n",
" # Count the number of values in each group\n",
" pl.count(\"random\").alias(\"size\"),\n",
" # Sample one element in each group\n",
" pl.col(\"names\").apply(lambda group_df: group_df.sample(1)),\n",
" pl.col(\"names\").map_elements(lambda group_df: group_df.sample(1)),\n",
" ]\n",
")"
]
Expand Down Expand Up @@ -607,7 +610,7 @@
"outputs": [],
"source": [
"# Add a new column to the DataFrame\n",
"df.with_column((pl.col(\"random\") * pl.col(\"nrs\")).alias(\"product\"))"
"df.with_columns((pl.col(\"random\") * pl.col(\"nrs\")).alias(\"product\"))"
]
},
{
Expand All @@ -621,7 +624,7 @@
"df.with_columns(\n",
" [\n",
" (pl.col(\"random\") * pl.col(\"nrs\")).alias(\"product\"),\n",
" pl.col(\"names\").str.lengths().alias(\"names_lengths\"),\n",
" pl.col(\"names\").str.len_bytes().alias(\"names_len_bytes\"),\n",
" ]\n",
")"
]
Expand All @@ -634,7 +637,7 @@
"outputs": [],
"source": [
"# Add a column at index 0 that counts the rows\n",
"df.with_row_count()"
"df.with_row_index()"
]
},
{
Expand Down Expand Up @@ -684,8 +687,8 @@
" pl.col(\"random\").rolling_skew(window_size=2).alias(\"rolling_skew\"),\n",
" # Rolling custom function\n",
" pl.col(\"random\")\n",
" .rolling_apply(function=np.nanstd, window_size=2)\n",
" .alias(\"rolling_apply\"),\n",
" .rolling_map(function=np.nanstd, window_size=2)\n",
" .alias(\"rolling_map\"),\n",
" ]\n",
")"
]
Expand Down
Loading