check in notebook code #23
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,179 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 1, | ||
| "id": "mighty-ukraine", | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "storage not configured, falling back to sample, default configuration\n", | ||
| "Connecting to database URL localhost\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "# import logging\n", | ||
| "import emission.core.get_database as edb\n", | ||
| "import emission.analysis.modelling.tour_model.similarity as similarity\n", | ||
| "import pandas as pd\n", | ||
| "import numpy as np\n", | ||
| "import get_request_percentage as grp\n", | ||
| "import get_scores as gs\n", | ||
| "import label_processing as lp\n", | ||
| "import get_users as gu\n", | ||
| "import data_preprocessing as preprocess\n", | ||
| "import get_tuning_score as tuning\n", | ||
| "import evaluation_pipeline as ep\n", | ||
| "import matplotlib.pyplot as plt\n", | ||
| "import get_plot as plot\n", | ||
| "import emission.core.common as ecc" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 2, | ||
| "id": "cathedral-pointer", | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "participant_uuid_obj = list(edb.get_profile_db().find({\"install_group\": \"participant\"}, {\"user_id\": 1, \"_id\": 0}))\n", | ||
| "all_users = [u[\"user_id\"] for u in participant_uuid_obj]" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 3, | ||
| "id": "exotic-livestock", | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "radius = 100" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "powered-airfare", | ||
| "metadata": { | ||
| "scrolled": true | ||
| }, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "user 1 filter_trips len 207\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "# get all/valid user list\n", | ||
| "user_ls, valid_users = gu.get_user_ls(all_users, radius)\n", | ||
| "\n", | ||
| "# collect request percentage for the first or second round (requested trips / total trips) for all users\n", | ||
| "all_percentage_first_tune = []\n", | ||
| "all_percentage_first_test = []\n", | ||
| "all_percentage_second_tune = []\n", | ||
| "all_percentage_second_test = []\n", | ||
| "\n", | ||
| "# collect homogeneity score for the first/second round for all users\n", | ||
| "all_homogeneity_score_first_tune = []\n", | ||
| "all_homogeneity_score_first_test = []\n", | ||
| "all_homogeneity_score_second_tune = []\n", | ||
| "all_homogeneity_score_second_test = []\n", | ||
| "\n", | ||
| "for a in range(len(all_users)):\n", | ||
| " user = all_users[a]\n", | ||
| " trips = preprocess.read_data(user)\n", | ||
| " filter_trips = preprocess.filter_data(trips, radius)\n", | ||
| " print('user', a + 1, 'filter_trips len', len(filter_trips))\n", | ||
| "\n", | ||
| " # filter out users that don't have enough valid labeled trips\n", | ||
| " if not gu.valid_user(filter_trips, trips):\n", | ||
| " continue\n", | ||
| " tune_idx, test_idx = preprocess.split_data(filter_trips)\n", | ||
| "\n", | ||
| " # choose tuning/test set to run the model\n", | ||
| " # this step will use KFold (5 splits) to split the data into different subsets\n", | ||
| " # - tune: tuning set\n", | ||
| " # - test: test set\n", | ||
| " # Here we user a bigger part of the data for testing and a smaller part for tuning\n", | ||
| " tune_data = preprocess.get_subdata(filter_trips, test_idx)\n", | ||
| " test_data = preprocess.get_subdata(filter_trips, tune_idx)\n", | ||
| "\n", | ||
| " pct_collect_first, homo_collect_first, pct_collect_second, homo_collect_second = ep.init_score()\n", | ||
|
There was a problem hiding this comment. If you have so much state, it seems like it would be better to have a class that encapsulates it. |
||
| " \n", | ||
| " # collect tuning parameters\n", | ||
| " coll_tune_score = []\n", | ||
| " coll_tradeoffs = []\n", | ||
| " # tuning\n", | ||
| " pct_collect_first,homo_collect_first,pct_collect_second,homo_collect_second,coll_tradeoffs, coll_tune_score= ep.tuning_test(tune_data,radius,pct_collect_first,homo_collect_first,pct_collect_second,homo_collect_second,coll_tradeoffs,coll_tune_score,tune = True)\n", | ||
shankari marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| "\n", | ||
| " pct_collect_first, homo_collect_first, pct_collect_second, homo_collect_second = ep.init_score()\n", | ||
| " # testing\n", | ||
| " pct_collect_first,homo_collect_first,pct_collect_second,homo_collect_second,coll_tradeoffs,coll_tune_score = ep.tuning_test(test_data,radius, pct_collect_first, homo_collect_first,pct_collect_second,homo_collect_second, coll_tradeoffs,coll_tune_score,test=True)\n", | ||
|
There was a problem hiding this comment. why do we return There was a problem hiding this comment. At this point, I am not sure if we still need the tradeoffs after the clustering, so I keep it. |
||
| "\n", | ||
| " print('colle_tune_score ', coll_tune_score)\n", | ||
| " print('coll_tradeoffs',coll_tradeoffs)\n", | ||
| "\n", | ||
| " # collect request percentage for the first round for all users\n", | ||
| " all_percentage_first_test.append(pct_collect_first)\n", | ||
| "\n", | ||
| " # collect homogeneity score for the first round for all users\n", | ||
| " all_homogeneity_score_first_test.append(homo_collect_first)\n", | ||
| "\n", | ||
| " # collect request percentage for the second round for all users\n", | ||
| " all_percentage_second_test.append(pct_collect_second)\n", | ||
| "\n", | ||
| " # collect homogeneity score for the second round for all users\n", | ||
| " all_homogeneity_score_second_test.append(homo_collect_second)\n", | ||
| "\n", | ||
| "print('all_percentage_first_test', all_percentage_first_test)\n", | ||
| "print('all_homogeneity_score_first_test', all_homogeneity_score_first_test)\n", | ||
| "print('all_percentage_second_test', all_percentage_second_test)\n", | ||
| "print('all_homogeneity_score_second_test', all_homogeneity_score_second_test)\n", | ||
| "\n", | ||
| "# plot evaluation scatter for the first round\n", | ||
| "plt.figure()\n", | ||
| "plot.get_scatter(all_percentage_first_test, all_homogeneity_score_first_test, valid_users)\n", | ||
| "\n", | ||
| "# plot evaluation scatter for the second round\n", | ||
| "plt.figure()\n", | ||
| "plot.get_scatter(all_percentage_second_test, all_homogeneity_score_second_test, valid_users)" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": null, | ||
| "id": "variable-faculty", | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [] | ||
| } | ||
| ], | ||
| "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": "3.7.9" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 5 | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@corinne-hcr The participant UUID check was specific to the CanBikeCO mini-pilot - it is not true for other programs or datasets. I have created a new mongodump of only the participant data, you should load that instead and change this to the call from
emission.storage.timeseries.abstract_timeseries