-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'dev' into bwmac/IBCDPE-794/proteomics_gx
- Loading branch information
Showing
23 changed files
with
808 additions
and
21 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,243 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "import synapseclient\n", | ||
| "\n", | ||
| "import great_expectations as gx\n", | ||
| "\n", | ||
| "context = gx.get_context(project_root_dir='../src/agoradatatools/great_expectations')\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "# Create Expectation Suite for RNA Distribution Data" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Get Example Data File" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "syn = synapseclient.Synapse()\n", | ||
| "syn.login()\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "rna_distribution_data_file = syn.get(\"syn28094691\").path\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Create Validator Object on Data File" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "validator = context.sources.pandas_default.read_json(\n", | ||
| " rna_distribution_data_file\n", | ||
| ")\n", | ||
| "validator.expectation_suite_name = \"rna_distribution_data\"\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Add Expectations to Validator Object For Each Column" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# model\n", | ||
| "validator.expect_column_values_to_be_of_type(\"model\", \"str\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"model\")\n", | ||
| "validator.expect_column_values_to_be_in_set(\"model\", [\"AD Diagnosis (males and females)\", \"AD Diagnosis x AOD (males and females)\",\"AD Diagnosis x Sex (females only)\", \"AD Diagnosis x Sex (males only)\"])" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# tissue\n", | ||
| "validator.expect_column_values_to_be_of_type(\"tissue\", \"str\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"tissue\")\n", | ||
| "validator.expect_column_values_to_be_in_set(\"tissue\", [\"CBE\", \"DLPFC\", \"FP\", \"IFG\", \"PHG\", \"STG\", \"TCX\", \"ACC\", \"PCC\"])" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# min\n", | ||
| "validator.expect_column_values_to_be_of_type(\"min\", \"float\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"min\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# max\n", | ||
| "validator.expect_column_values_to_be_of_type(\"max\", \"float\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"max\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# median\n", | ||
| "validator.expect_column_values_to_be_of_type(\"median\", \"float\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"median\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# first_quartile\n", | ||
| "validator.expect_column_values_to_be_of_type(\"first_quartile\", \"float\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"first_quartile\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# third_quartile\n", | ||
| "validator.expect_column_values_to_be_of_type(\"third_quartile\", \"float\")\n", | ||
| "validator.expect_column_values_to_not_be_null(\"third_quartile\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "# multi-field\n", | ||
| "validator.expect_column_pair_values_a_to_be_greater_than_b(\"max\", \"third_quartile\")\n", | ||
| "validator.expect_column_pair_values_a_to_be_greater_than_b(\"third_quartile\", \"median\")\n", | ||
| "validator.expect_column_pair_values_a_to_be_greater_than_b(\"median\", \"first_quartile\")\n", | ||
| "validator.expect_column_pair_values_a_to_be_greater_than_b(\"first_quartile\", \"min\")" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Save Expectation Suite" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "validator.save_expectation_suite(discard_failed_expectations=False)\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Create Checkpoint and View Results" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "checkpoint = context.add_or_update_checkpoint(\n", | ||
| " name=\"agora-test-checkpoint\",\n", | ||
| " validator=validator,\n", | ||
| ")\n", | ||
| "checkpoint_result = checkpoint.run()\n", | ||
| "context.view_validation_result(checkpoint_result)\n" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "markdown", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "## Build Data Docs - Click on Expectation Suite to View All Expectations" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "context.build_data_docs()\n", | ||
| "context.open_data_docs()\n" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "Python 3", | ||
| "language": "python", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.9.13" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,25 @@ | ||
| """Function for transforming proteomics data. This function is called on all three proteomics | ||
| data sets, although currently it only affects the LFQ data set as it is the only one with "CON__" | ||
| entries. | ||
| """ | ||
|
|
||
| import pandas as pd | ||
|
|
||
|
|
||
| def transform_proteomics(df: pd.DataFrame) -> pd.DataFrame: | ||
| """Filters out rows that have "CON__" in their uniqid. This label indicates that the protein | ||
| is a known contaminant and should be removed from the final data set. Rows with an NA uniqid | ||
| are also removed. | ||
| Args: | ||
| df (pd.DataFrame]): pandas DataFrame containing proteomics data. Must contain a column | ||
| called "uniqid". | ||
| Returns: | ||
| pd.DataFrame: a DataFrame that is identical to the input DataFrame but with rows containing | ||
| "CON__" in the uniqid removed. | ||
| """ | ||
| # Using "na=True" causes rows with NA uniqids to be set to True so they get removed | ||
| remove_rows = df["uniqid"].str.contains("CON__", na=True) | ||
| df = df.drop(df.index[remove_rows]) | ||
| return df |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.