diff --git a/tcmi.ipynb b/tcmi.ipynb index 17c5d3f260e40ec6c862d8e0475d4f96f44a240d..2f79970547622cd760f2a5b871adff52429b182f 100644 --- a/tcmi.ipynb +++ b/tcmi.ipynb @@ -57,8 +57,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-11-11T17:36:57.497040Z", - "start_time": "2021-11-11T17:36:57.488774Z" + "end_time": "2022-04-02T13:41:21.180813Z", + "start_time": "2022-04-02T13:41:21.179355Z" }, "init_cell": true }, @@ -82,8 +82,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-11-11T17:36:58.898232Z", - "start_time": "2021-11-11T17:36:57.498482Z" + "end_time": "2022-04-02T13:41:21.714829Z", + "start_time": "2022-04-02T13:41:21.181711Z" }, "hidden": true, "init_cell": true @@ -179,8 +179,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:36.476498Z", - "start_time": "2020-02-06T20:01:36.469713Z" + "end_time": "2022-04-02T13:41:21.718036Z", + "start_time": "2022-04-02T13:41:21.716101Z" }, "hidden": true }, @@ -225,8 +225,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:36.578237Z", - "start_time": "2020-02-06T20:01:36.481310Z" + "end_time": "2022-04-02T13:41:21.745900Z", + "start_time": "2022-04-02T13:41:21.719319Z" }, "hidden": true }, @@ -319,8 +319,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:37.268567Z", - "start_time": "2020-02-06T20:01:36.584168Z" + "end_time": "2022-04-02T13:41:22.028013Z", + "start_time": "2022-04-02T13:41:21.747739Z" }, "hidden": true, "hide_input": false @@ -409,8 +409,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:37.410841Z", - "start_time": "2020-02-06T20:01:37.278460Z" + "end_time": "2022-04-02T13:41:22.065037Z", + "start_time": "2022-04-02T13:41:22.036208Z" }, "hidden": true, "scrolled": true @@ -468,8 +468,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:38.318289Z", - "start_time": "2020-02-06T20:01:37.421003Z" + "end_time": "2022-04-02T13:41:22.390648Z", + "start_time": "2022-04-02T13:41:22.066008Z" }, "hidden": true }, @@ -588,50 +588,6 @@ "plt.show()" ] }, - { - "cell_type": "markdown", - "metadata": { - "heading_collapsed": true, - "hidden": true - }, - "source": [ - "### 1.4. Invariance against scaling" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "hidden": true - }, - "source": [ - "**Test**: Invariance of TCMI against invertible transformations<br />\n", - "**Expected**: Same score (here: showcases some very simple examples)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.122288Z", - "start_time": "2020-02-06T20:01:38.339997Z" - }, - "hidden": true - }, - "outputs": [], - "source": [ - "short_size = 50\n", - "xx = 2 * np.random.random_sample(short_size) - 1\n", - "yy = np.linspace(0, 1, num=short_size)\n", - "\n", - "target = 'y'\n", - "data = pd.DataFrame({'y': yy, 'x1': xx, 'x2': np.exp(xx), 'x3': xx**3 + xx})\n", - "\n", - "estimator = DependenceEstimator(method='tcmi', n_jobs=-1)\n", - "get_subspaces(data, target, estimator, cv=None, verbose=1, depth=1,\n", - " scoring='mutual_information_score', n_jobs=-1);" - ] - }, { "cell_type": "markdown", "metadata": { @@ -657,8 +613,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.194903Z", - "start_time": "2020-02-06T20:01:44.138636Z" + "end_time": "2022-04-02T13:41:22.393710Z", + "start_time": "2022-04-02T13:41:22.391695Z" }, "hidden": true }, @@ -691,8 +647,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.310396Z", - "start_time": "2020-02-06T20:01:44.203485Z" + "end_time": "2022-04-02T13:41:22.409353Z", + "start_time": "2022-04-02T13:41:22.394686Z" }, "hidden": true }, @@ -745,8 +701,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.380950Z", - "start_time": "2020-02-06T20:01:44.320839Z" + "end_time": "2022-04-02T13:41:22.419820Z", + "start_time": "2022-04-02T13:41:22.410854Z" }, "hidden": true }, @@ -795,8 +751,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.492316Z", - "start_time": "2020-02-06T20:01:44.415300Z" + "end_time": "2022-04-02T13:41:22.432717Z", + "start_time": "2022-04-02T13:41:22.423142Z" }, "hidden": true }, @@ -847,8 +803,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.598306Z", - "start_time": "2020-02-06T20:01:44.501472Z" + "end_time": "2022-04-02T13:41:22.452058Z", + "start_time": "2022-04-02T13:41:22.433673Z" }, "hidden": true, "scrolled": true @@ -933,8 +889,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:44.841663Z", - "start_time": "2020-02-06T20:01:44.602723Z" + "end_time": "2022-04-02T13:41:22.493797Z", + "start_time": "2022-04-02T13:41:22.453115Z" }, "code_folding": [ 0, @@ -1092,8 +1048,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:45.959653Z", - "start_time": "2020-02-06T20:01:44.869348Z" + "end_time": "2022-04-02T13:41:22.840051Z", + "start_time": "2022-04-02T13:41:22.494727Z" }, "code_folding": [], "hidden": true @@ -1252,8 +1208,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:46.090055Z", - "start_time": "2020-02-06T20:01:45.980293Z" + "end_time": "2022-04-02T13:41:22.842898Z", + "start_time": "2022-04-02T13:41:22.841105Z" }, "hidden": true }, @@ -1277,8 +1233,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:46.302638Z", - "start_time": "2020-02-06T20:01:46.105784Z" + "end_time": "2022-04-02T13:41:22.866724Z", + "start_time": "2022-04-02T13:41:22.843820Z" }, "hidden": true }, @@ -1345,8 +1301,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:46.620148Z", - "start_time": "2020-02-06T20:01:46.315591Z" + "end_time": "2022-04-02T13:41:22.926403Z", + "start_time": "2022-04-02T13:41:22.868157Z" }, "hidden": true, "scrolled": true @@ -1411,14 +1367,18 @@ }, { "cell_type": "markdown", - "metadata": {}, + "metadata": { + "heading_collapsed": true + }, "source": [ "## 4. Octet-binary compound semiconductors" ] }, { "cell_type": "markdown", - "metadata": {}, + "metadata": { + "hidden": true + }, "source": [ "Octet-binary compound semiconductors are materials consisting of two elements formed by groups of I/VII, II/VI, III/V, or IV/IV elements leading to a full valence shell. They crystallize in rock salt (RS) or zinc blende (ZB) structures.\n", "\n", @@ -1443,7 +1403,8 @@ "ExecuteTime": { "end_time": "2020-01-14T11:32:15.336979Z", "start_time": "2020-01-14T11:32:15.333046Z" - } + }, + "hidden": true }, "source": [ "**Test**: Optimal feature subset search<br />\n", @@ -1455,9 +1416,10 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2020-02-06T20:01:46.843772Z", - "start_time": "2020-02-06T20:01:46.664345Z" + "end_time": "2022-04-02T13:41:22.957933Z", + "start_time": "2022-04-02T13:41:22.928291Z" }, + "hidden": true, "scrolled": false }, "outputs": [], @@ -1533,7 +1495,7 @@ "metadata": { "hide_input": false, "kernelspec": { - "display_name": "Python 3 (ipykernel)", + "display_name": "Python 3", "language": "python", "name": "python3" }, @@ -1547,7 +1509,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.7" + "version": "3.7.3" }, "toc": { "base_numbering": "0",