Deployed c8dbd5c5 to dev with MkDocs 1.2.1 and mike 1.0.1

gh-pages
github-actions 2021-07-01 22:29:54 +00:00
parent a245ad1c4c
commit 726cd1d4b8
3 changed files with 28 additions and 11 deletions

View File

@ -1855,7 +1855,7 @@
</tr> </tr>
<tr> <tr>
<td><code>[INCLUDE_EPISODE_FEATURES]</code></td> <td><code>[INCLUDE_EPISODE_FEATURES]</code></td>
<td>Set to <code>True</code> to extract application episode features as well from the <code>RAPIDS</code> provider</td> <td>Set to <code>True</code> to extract features from application usage episodes using Screen data</td>
</tr> </tr>
<tr> <tr>
<td><code>[FEATURES]</code></td> <td><code>[FEATURES]</code></td>
@ -1863,15 +1863,15 @@
</tr> </tr>
<tr> <tr>
<td><code>[SINGLE_CATEGORIES]</code></td> <td><code>[SINGLE_CATEGORIES]</code></td>
<td>An array of app categories to be <em>included</em> in the feature extraction computation. The special keyword <code>all</code> represents a category with all the apps from each participant. By default we use the category catalogue pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td> <td>An array of app categories to be <em>included</em> in the feature extraction computation. The special keyword <code>all</code> represents a category with all the apps from each participant. By default, we use the category catalog pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td>
</tr> </tr>
<tr> <tr>
<td><code>[CUSTOM_CATEGORIES]</code></td> <td><code>[CUSTOM_CATEGORIES]</code></td>
<td>An array of collections representing your own app categories. They key of each element is the name of the in-house category and the value is an array of the package names (apps) included in that category.</td> <td>An array of collections representing your own app categories. The key of each element is the name of the custom category, and the value is an array of the package names (apps) included in that category.</td>
</tr> </tr>
<tr> <tr>
<td><code>[MULTIPLE_CATEGORIES]</code></td> <td><code>[MULTIPLE_CATEGORIES]</code></td>
<td>An array of collections representing meta-categories (a group of categories). They key of each element is the name of the <code>meta-category</code> and the value is an array of member app categories. By default we use the category catalogue pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td> <td>An array of collections representing meta-categories (a group of categories). The key of each element is the name of the <code>meta-category</code> and the value is an array of member app categories. By default, we use the category catalog pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td>
</tr> </tr>
<tr> <tr>
<td><code>[SINGLE_APPS]</code></td> <td><code>[SINGLE_APPS]</code></td>
@ -1879,7 +1879,7 @@
</tr> </tr>
<tr> <tr>
<td><code>[EXCLUDED_CATEGORIES]</code></td> <td><code>[EXCLUDED_CATEGORIES]</code></td>
<td>An array of app categories to be <em>excluded</em> from the feature extraction computation. By default we use the category catalogue pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td> <td>An array of app categories to be <em>excluded</em> from the feature extraction computation. By default, we use the category catalog pointed by <code>[APPLICATION_CATEGORIES][CATALOGUE_FILE]</code> (see the Sensor parameters description table above)</td>
</tr> </tr>
<tr> <tr>
<td><code>[EXCLUDED_APPS]</code></td> <td><code>[EXCLUDED_APPS]</code></td>
@ -1898,7 +1898,7 @@
</thead> </thead>
<tbody> <tbody>
<tr> <tr>
<td>count</td> <td>countevent</td>
<td>apps</td> <td>apps</td>
<td>Number of times a single app or apps within a category were used (i.e. they were brought to the foreground either by tapping their icon or switching to it from another app)</td> <td>Number of times a single app or apps within a category were used (i.e. they were brought to the foreground either by tapping their icon or switching to it from another app)</td>
</tr> </tr>
@ -1918,6 +1918,11 @@
<td>The entropy of the used apps within a category during a <code>time_segment</code> (each app is seen as a unique event, the more apps were used, the higher the entropy). This is especially relevant when computed over all apps. Entropy cannot be obtained for a single app</td> <td>The entropy of the used apps within a category during a <code>time_segment</code> (each app is seen as a unique event, the more apps were used, the higher the entropy). This is especially relevant when computed over all apps. Entropy cannot be obtained for a single app</td>
</tr> </tr>
<tr> <tr>
<td>countepisode</td>
<td>apps</td>
<td>Number of times a usage episode of a single app or apps within a category were logged. In contrast to <code>countevent</code>, if an app was used across more than one time segment (for example, across more than one 30-minute segment), the <code>countepisode</code> will be one on each time segment instance.</td>
</tr>
<tr>
<td>minduration</td> <td>minduration</td>
<td>minutes</td> <td>minutes</td>
<td>For a <code>time_segment</code>, the minimum duration an application was used in minutes</td> <td>For a <code>time_segment</code>, the minimum duration an application was used in minutes</td>
@ -1941,11 +1946,23 @@
</table> </table>
<div class="admonition note"> <div class="admonition note">
<p class="admonition-title">Assumptions/Observations</p> <p class="admonition-title">Assumptions/Observations</p>
<p>Features can be computed by app, by apps grouped under a single category (genre) and by multiple categories grouped together (meta-categories). For example, we can get features for <code>Facebook</code> (single app), for <code>Social Network</code> apps (a category including Facebook and other social media apps) or for <code>Social</code> (a meta-category formed by <code>Social Network</code> and <code>Social Media Tools</code> categories).</p> <ol>
<li>
<p>Features can be computed by app, by apps grouped under a single category (genre), by your own categories, or by multiple categories grouped together (meta-categories). For example, we can get features for <code>Facebook</code> (single app), for <code>Social Network</code> apps (a category including Facebook and other social media apps), for <code>Traditional Social Media</code> (a custom category that includes Twitter and Facebook), or for <code>Social</code> (a meta-category formed by <code>Social Network</code> and <code>Social Media Tools</code> categories).</p>
</li>
<li>
<p>Apps installed by default like YouTube are considered systems apps on some phones. We do an exact match to exclude apps where &ldquo;genre&rdquo; == <code>EXCLUDED_CATEGORIES</code> or &ldquo;package_name&rdquo; == <code>EXCLUDED_APPS</code>.</p> <p>Apps installed by default like YouTube are considered systems apps on some phones. We do an exact match to exclude apps where &ldquo;genre&rdquo; == <code>EXCLUDED_CATEGORIES</code> or &ldquo;package_name&rdquo; == <code>EXCLUDED_APPS</code>.</p>
<p>We provide three ways of classifying and app within a category (genre): a) by automatically scraping its official category from the Google Play Store, b) by using the catalogue created by Stachl et al. which we provide in RAPIDS (<code>data/external/stachl_application_genre_catalogue.csv</code>), or c) by manually creating a personalized catalogue. You can choose a, b or c by modifying <code>[APPLICATION_GENRES]</code> keys and values (see the Sensor parameters description table above).</p> </li>
<p>We count <code>episodes</code> and <code>events</code> seperatly. Events are single logs, but episodes will span from a start to and end date time and they will be chunked across any overlapping time segments. And we also compute <code>top1global</code> seperatly. <code>top1global</code> of <code>episodes</code> might not be the same as the <code>top1global</code> of <code>events</code>.</p> <li>
<p>The application episodes are calculated using the application foreground and screen unlock episode data. An application episode starts when the application is launched and ends when either, a new application is launched or the screen is locked.</p> <p>We provide four ways of classifying an app within a category (genre): a) by automatically scraping its official category from the Google Play Store, b) by using the catalog created by Stachl et al., which we provide in RAPIDS (<code>data/external/stachl_application_genre_catalogue.csv</code>), c) by manually creating a personalized catalog, or d) by defining a custom category in <code>config.yaml</code>. You can choose a, b, or c by modifying <code>[APPLICATION_GENRES]</code> keys and values (see the first table of this page).</p>
</li>
<li>
<p>We count <code>episodes</code> and <code>events</code> separately. Events are single app logs (when an app was opened), but episodes span from the time an app was opened until a new app is in the foreground or the screen is locked. Episodes will be chunked across any overlapping time segments. The <code>top1global</code> of <code>episodes</code> might not be the same as the <code>top1global</code> of <code>events</code>.</p>
</li>
<li>
<p>The application episodes are calculated using the application foreground and screen unlock episode data. An application episode starts when the application is launched and ends when new application is launched, or the screen is locked.</p>
</li>
</ol>
</div> </div>

File diff suppressed because one or more lines are too long

Binary file not shown.