attempt to fix F_Neighbors2
[talweg.git] / reports / report.ipynb
CommitLineData
ff5df8e3
BA
1{
2 "cells": [
3 {
4 "cell_type": "markdown",
83a13103 5 "metadata": {},
ff5df8e3
BA
6 "source": [
7 "\n",
8 "\n",
9 "<h2>Introduction</h2>\n",
10 "\n",
11 "J'ai fait quelques essais dans différentes configurations pour la méthode \"Neighbors\"\n",
6774e53d
BA
12 "(la seule dont on a parlé) et sa variante récente appelée pour l'instant \"Neighbors2\",\n",
13 "avec simtype=\"mix\" : deux types de similarités prises en compte, puis multiplication des poids.\n",
14 "Pour Neighbors on prédit le saut (par la moyenne pondérée des sauts passés), et pour Neighbors2\n",
15 "on n'effectue aucun raccordement (prévision directe).\n",
ff5df8e3 16 "\n",
6774e53d
BA
17 "J'ai systématiquement comparé à une approche naïve : la moyenne des lendemains des jours\n",
18 "\"similaires\" dans tout le passé, ainsi qu'à la persistence -- reproduisant le jour courant ou\n",
19 "allant chercher le futur similaire une semaine avant.\n",
ff5df8e3
BA
20 "\n",
21 "Ensuite j'affiche les erreurs, quelques courbes prévues/mesurées, quelques filaments puis les\n",
22 "histogrammes de quelques poids. Concernant les graphes de filaments, la moitié gauche du graphe\n",
23 "correspond aux jours similaires au jour courant, tandis que la moitié droite affiche les\n",
24 "lendemains : ce sont donc les voisinages tels qu'utilisés dans l'algorithme.\n",
25 "\n"
26 ]
27 },
28 {
29 "cell_type": "code",
30 "execution_count": null,
83a13103 31 "metadata": {},
ff5df8e3
BA
32 "outputs": [],
33 "source": [
34 "library(talweg)\n",
35 "\n",
6774e53d
BA
36 "P = 7 #instant de prévision\n",
37 "H = 17 #horizon (en heures)\n",
38 "\n",
ff5df8e3
BA
39 "ts_data = read.csv(system.file(\"extdata\",\"pm10_mesures_H_loc_report.csv\",package=\"talweg\"))\n",
40 "exo_data = read.csv(system.file(\"extdata\",\"meteo_extra_noNAs.csv\",package=\"talweg\"))\n",
6774e53d
BA
41 "# NOTE: 'GMT' because DST gaps are filled and multiple values merged in above dataset.\n",
42 "# Prediction from P+1 to P+H included.\n",
43 "data = getData(ts_data, exo_data, input_tz = \"GMT\", working_tz=\"GMT\", predict_at=P)\n",
ff5df8e3
BA
44 "\n",
45 "indices_ch = seq(as.Date(\"2015-01-18\"),as.Date(\"2015-01-24\"),\"days\")\n",
46 "indices_ep = seq(as.Date(\"2015-03-15\"),as.Date(\"2015-03-21\"),\"days\")\n",
6774e53d 47 "indices_np = seq(as.Date(\"2015-04-26\"),as.Date(\"2015-05-02\"),\"days\")\n"
ff5df8e3
BA
48 ]
49 },
50 {
51 "cell_type": "markdown",
83a13103 52 "metadata": {},
ff5df8e3 53 "source": [
6774e53d
BA
54 "\n",
55 "\n",
ff5df8e3
BA
56 "<h2 style=\"color:blue;font-size:2em\">Pollution par chauffage</h2>"
57 ]
58 },
59 {
60 "cell_type": "code",
61 "execution_count": null,
83a13103 62 "metadata": {},
ff5df8e3
BA
63 "outputs": [],
64 "source": [
6774e53d 65 "p_nn = computeForecast(data, indices_ch, \"Neighbors\", \"Neighbors\", horizon=H)\n",
83a13103 66 "p_nn2 = computeForecast(data, indices_ch, \"Neighbors2\", \"Zero\", horizon=H)\n",
6774e53d
BA
67 "p_az = computeForecast(data, indices_ch, \"Average\", \"Zero\", horizon=H)\n",
68 "p_pz = computeForecast(data, indices_ch, \"Persistence\", \"Zero\", horizon=H, same_day=TRUE)"
a866acb3
BA
69 ]
70 },
71 {
72 "cell_type": "code",
73 "execution_count": null,
83a13103 74 "metadata": {},
ff5df8e3
BA
75 "outputs": [],
76 "source": [
6774e53d
BA
77 "e_nn = computeError(data, p_nn, H)\n",
78 "e_nn2 = computeError(data, p_nn2, H)\n",
79 "e_az = computeError(data, p_az, H)\n",
80 "e_pz = computeError(data, p_pz, H)\n",
81 "options(repr.plot.width=9, repr.plot.height=7)\n",
82 "plotError(list(e_nn, e_pz, e_az, e_nn2), cols=c(1,2,colors()[258], 4))\n",
83 "\n",
84 "# Noir: Neighbors, bleu: Neighbors2, vert: moyenne, rouge: persistence\n",
85 "\n",
86 "i_np = which.min(e_nn$abs$indices)\n",
87 "i_p = which.max(e_nn$abs$indices)"
ff5df8e3
BA
88 ]
89 },
90 {
91 "cell_type": "code",
92 "execution_count": null,
83a13103 93 "metadata": {},
ff5df8e3
BA
94 "outputs": [],
95 "source": [
96 "options(repr.plot.width=9, repr.plot.height=4)\n",
97 "par(mfrow=c(1,2))\n",
98 "\n",
6774e53d
BA
99 "plotPredReal(data, p_nn, i_np); title(paste(\"PredReal nn day\",i_np))\n",
100 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn day\",i_p))\n",
101 "\n",
102 "plotPredReal(data, p_nn2, i_np); title(paste(\"PredReal nn2 day\",i_np))\n",
103 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn2 day\",i_p))\n",
ff5df8e3 104 "\n",
6774e53d
BA
105 "plotPredReal(data, p_az, i_np); title(paste(\"PredReal az day\",i_np))\n",
106 "plotPredReal(data, p_az, i_p); title(paste(\"PredReal az day\",i_p))\n",
ff5df8e3
BA
107 "\n",
108 "# Bleu: prévue, noir: réalisée"
109 ]
110 },
111 {
112 "cell_type": "code",
113 "execution_count": null,
83a13103 114 "metadata": {},
ff5df8e3
BA
115 "outputs": [],
116 "source": [
117 "par(mfrow=c(1,2))\n",
6774e53d
BA
118 "f_np = computeFilaments(data, p_nn, i_np, plot=TRUE); title(paste(\"Filaments nn day\",i_np))\n",
119 "f_p = computeFilaments(data, p_nn, i_p, plot=TRUE); title(paste(\"Filaments nn day\",i_p))\n",
ff5df8e3 120 "\n",
6774e53d
BA
121 "f_np2 = computeFilaments(data, p_nn2, i_np, plot=TRUE); title(paste(\"Filaments nn2 day\",i_np))\n",
122 "f_p2 = computeFilaments(data, p_nn2, i_p, plot=TRUE); title(paste(\"Filaments nn2 day\",i_p))"
ff5df8e3
BA
123 ]
124 },
125 {
126 "cell_type": "code",
127 "execution_count": null,
83a13103 128 "metadata": {},
ff5df8e3
BA
129 "outputs": [],
130 "source": [
131 "par(mfrow=c(1,2))\n",
83a13103
BA
132 "plotFilamentsBox(data, f_np); title(paste(\"FilBox nn day\",i_np))\n",
133 "plotFilamentsBox(data, f_p); title(paste(\"FilBox nn day\",i_p))\n",
ff5df8e3 134 "\n",
83a13103
BA
135 "# Generally too few neighbors:\n",
136 "#plotFilamentsBox(data, f_np2); title(paste(\"FilBox nn2 day\",i_np))\n",
ea5c7e56
BA
137 "#plotFilamentsBox(data, f_p2); title(paste(\"FilBox nn2 day\",i_p))"
138 ]
139 },
140 {
141 "cell_type": "code",
142 "execution_count": null,
83a13103 143 "metadata": {},
ff5df8e3
BA
144 "outputs": [],
145 "source": [
146 "par(mfrow=c(1,2))\n",
6774e53d
BA
147 "plotRelVar(data, f_np); title(paste(\"StdDev nn day\",i_np))\n",
148 "plotRelVar(data, f_p); title(paste(\"StdDev nn day\",i_p))\n",
ff5df8e3 149 "\n",
6774e53d
BA
150 "plotRelVar(data, f_np2); title(paste(\"StdDev nn2 day\",i_np))\n",
151 "plotRelVar(data, f_p2); title(paste(\"StdDev nn2 day\",i_p))\n",
ff5df8e3
BA
152 "\n",
153 "# Variabilité globale en rouge ; sur les 60 voisins (+ lendemains) en noir"
154 ]
155 },
156 {
157 "cell_type": "code",
158 "execution_count": null,
83a13103 159 "metadata": {},
ff5df8e3
BA
160 "outputs": [],
161 "source": [
162 "par(mfrow=c(1,2))\n",
6774e53d
BA
163 "plotSimils(p_nn, i_np); title(paste(\"Weights nn day\",i_np))\n",
164 "plotSimils(p_nn, i_p); title(paste(\"Weights nn day\",i_p))\n",
ff5df8e3 165 "\n",
6774e53d
BA
166 "plotSimils(p_nn2, i_np); title(paste(\"Weights nn2 day\",i_np))\n",
167 "plotSimils(p_nn2, i_p); title(paste(\"Weights nn2 day\",i_p))\n",
ff5df8e3
BA
168 "\n",
169 "# - pollué à gauche, + pollué à droite"
170 ]
171 },
172 {
173 "cell_type": "code",
174 "execution_count": null,
83a13103 175 "metadata": {},
ff5df8e3
BA
176 "outputs": [],
177 "source": [
6774e53d
BA
178 "# Fenêtres sélectionnées dans ]0,7] / nn à gauche, nn2 à droite\n",
179 "p_nn$getParams(i_np)$window\n",
180 "p_nn$getParams(i_p)$window\n",
ff5df8e3 181 "\n",
6774e53d
BA
182 "p_nn2$getParams(i_np)$window\n",
183 "p_nn2$getParams(i_p)$window"
ff5df8e3
BA
184 ]
185 },
186 {
187 "cell_type": "markdown",
83a13103 188 "metadata": {},
ff5df8e3
BA
189 "source": [
190 "\n",
191 "\n",
192 "<h2 style=\"color:blue;font-size:2em\">Pollution par épandage</h2>"
193 ]
194 },
195 {
196 "cell_type": "code",
197 "execution_count": null,
83a13103 198 "metadata": {},
ff5df8e3
BA
199 "outputs": [],
200 "source": [
6774e53d
BA
201 "p_nn = computeForecast(data, indices_ep, \"Neighbors\", \"Neighbors\", horizon=H)\n",
202 "p_nn2 = computeForecast(data, indices_ep, \"Neighbors2\", \"Zero\", horizon=H)\n",
203 "p_az = computeForecast(data, indices_ep, \"Average\", \"Zero\", horizon=H)\n",
204 "p_pz = computeForecast(data, indices_ep, \"Persistence\", \"Zero\", horizon=H, same_day=TRUE)"
ff5df8e3
BA
205 ]
206 },
207 {
208 "cell_type": "code",
209 "execution_count": null,
83a13103 210 "metadata": {},
ff5df8e3
BA
211 "outputs": [],
212 "source": [
6774e53d
BA
213 "e_nn = computeError(data, p_nn, H)\n",
214 "e_nn2 = computeError(data, p_nn2, H)\n",
215 "e_az = computeError(data, p_az, H)\n",
216 "e_pz = computeError(data, p_pz, H)\n",
ff5df8e3 217 "options(repr.plot.width=9, repr.plot.height=7)\n",
6774e53d 218 "plotError(list(e_nn, e_pz, e_az, e_nn2), cols=c(1,2,colors()[258], 4))\n",
ff5df8e3 219 "\n",
6774e53d 220 "# Noir: Neighbors, bleu: Neighbors2, vert: moyenne, rouge: persistence\n",
ff5df8e3 221 "\n",
6774e53d
BA
222 "i_np = which.min(e_nn$abs$indices)\n",
223 "i_p = which.max(e_nn$abs$indices)"
ff5df8e3
BA
224 ]
225 },
226 {
227 "cell_type": "code",
228 "execution_count": null,
83a13103 229 "metadata": {},
ff5df8e3
BA
230 "outputs": [],
231 "source": [
232 "options(repr.plot.width=9, repr.plot.height=4)\n",
233 "par(mfrow=c(1,2))\n",
234 "\n",
6774e53d
BA
235 "plotPredReal(data, p_nn, i_np); title(paste(\"PredReal nn day\",i_np))\n",
236 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn day\",i_p))\n",
ff5df8e3 237 "\n",
6774e53d
BA
238 "plotPredReal(data, p_nn2, i_np); title(paste(\"PredReal nn2 day\",i_np))\n",
239 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn2 day\",i_p))\n",
ff5df8e3
BA
240 "\n",
241 "plotPredReal(data, p_az, i_np); title(paste(\"PredReal az day\",i_np))\n",
242 "plotPredReal(data, p_az, i_p); title(paste(\"PredReal az day\",i_p))\n",
243 "\n",
244 "# Bleu: prévue, noir: réalisée"
245 ]
246 },
247 {
248 "cell_type": "code",
249 "execution_count": null,
83a13103 250 "metadata": {},
ff5df8e3
BA
251 "outputs": [],
252 "source": [
253 "par(mfrow=c(1,2))\n",
6774e53d
BA
254 "f_np = computeFilaments(data, p_nn, i_np, plot=TRUE); title(paste(\"Filaments nn day\",i_np))\n",
255 "f_p = computeFilaments(data, p_nn, i_p, plot=TRUE); title(paste(\"Filaments nn day\",i_p))\n",
ff5df8e3 256 "\n",
6774e53d
BA
257 "f_np2 = computeFilaments(data, p_nn2, i_np, plot=TRUE); title(paste(\"Filaments nn2 day\",i_np))\n",
258 "f_p2 = computeFilaments(data, p_nn2, i_p, plot=TRUE); title(paste(\"Filaments nn2 day\",i_p))"
ff5df8e3
BA
259 ]
260 },
261 {
262 "cell_type": "code",
263 "execution_count": null,
83a13103 264 "metadata": {},
ff5df8e3
BA
265 "outputs": [],
266 "source": [
267 "par(mfrow=c(1,2))\n",
6774e53d
BA
268 "plotFilamentsBox(data, f_np); title(paste(\"FilBox nn day\",i_np))\n",
269 "plotFilamentsBox(data, f_p); title(paste(\"FilBox nn day\",i_p))\n",
ff5df8e3 270 "\n",
83a13103
BA
271 "# Generally too few neighbors:\n",
272 "#plotFilamentsBox(data, f_np2); title(paste(\"FilBox nn2 day\",i_np))\n",
273 "#plotFilamentsBox(data, f_p2); title(paste(\"FilBox nn2 day\",i_p))"
ff5df8e3
BA
274 ]
275 },
276 {
277 "cell_type": "code",
278 "execution_count": null,
83a13103 279 "metadata": {},
ff5df8e3
BA
280 "outputs": [],
281 "source": [
282 "par(mfrow=c(1,2))\n",
6774e53d
BA
283 "plotRelVar(data, f_np); title(paste(\"StdDev nn day\",i_np))\n",
284 "plotRelVar(data, f_p); title(paste(\"StdDev nn day\",i_p))\n",
ff5df8e3 285 "\n",
6774e53d
BA
286 "plotRelVar(data, f_np2); title(paste(\"StdDev nn2 day\",i_np))\n",
287 "plotRelVar(data, f_p2); title(paste(\"StdDev nn2 day\",i_p))\n",
ff5df8e3
BA
288 "\n",
289 "# Variabilité globale en rouge ; sur les 60 voisins (+ lendemains) en noir"
290 ]
291 },
292 {
293 "cell_type": "code",
294 "execution_count": null,
83a13103 295 "metadata": {},
ff5df8e3
BA
296 "outputs": [],
297 "source": [
298 "par(mfrow=c(1,2))\n",
6774e53d
BA
299 "plotSimils(p_nn, i_np); title(paste(\"Weights nn day\",i_np))\n",
300 "plotSimils(p_nn, i_p); title(paste(\"Weights nn day\",i_p))\n",
ff5df8e3 301 "\n",
6774e53d
BA
302 "plotSimils(p_nn2, i_np); title(paste(\"Weights nn2 day\",i_np))\n",
303 "plotSimils(p_nn2, i_p); title(paste(\"Weights nn2 day\",i_p))\n",
ff5df8e3
BA
304 "\n",
305 "# - pollué à gauche, + pollué à droite"
306 ]
307 },
308 {
309 "cell_type": "code",
310 "execution_count": null,
83a13103 311 "metadata": {},
ff5df8e3
BA
312 "outputs": [],
313 "source": [
6774e53d
BA
314 "# Fenêtres sélectionnées dans ]0,7] / nn à gauche, nn2 à droite\n",
315 "p_nn$getParams(i_np)$window\n",
316 "p_nn$getParams(i_p)$window\n",
ff5df8e3 317 "\n",
6774e53d
BA
318 "p_nn2$getParams(i_np)$window\n",
319 "p_nn2$getParams(i_p)$window"
ff5df8e3
BA
320 ]
321 },
322 {
323 "cell_type": "markdown",
83a13103 324 "metadata": {},
ff5df8e3
BA
325 "source": [
326 "\n",
327 "\n",
328 "<h2 style=\"color:blue;font-size:2em\">Semaine non polluée</h2>"
329 ]
330 },
331 {
332 "cell_type": "code",
333 "execution_count": null,
83a13103 334 "metadata": {},
ff5df8e3
BA
335 "outputs": [],
336 "source": [
6774e53d
BA
337 "p_nn = computeForecast(data, indices_np, \"Neighbors\", \"Neighbors\", horizon=H)\n",
338 "p_nn2 = computeForecast(data, indices_np, \"Neighbors2\", \"Zero\", horizon=H)\n",
339 "p_az = computeForecast(data, indices_np, \"Average\", \"Zero\", horizon=H)\n",
340 "p_pz = computeForecast(data, indices_np, \"Persistence\", \"Zero\", horizon=H, same_day=FALSE)"
ff5df8e3
BA
341 ]
342 },
343 {
344 "cell_type": "code",
345 "execution_count": null,
83a13103 346 "metadata": {},
ff5df8e3
BA
347 "outputs": [],
348 "source": [
6774e53d
BA
349 "e_nn = computeError(data, p_nn, H)\n",
350 "e_nn2 = computeError(data, p_nn2, H)\n",
351 "e_az = computeError(data, p_az, H)\n",
352 "e_pz = computeError(data, p_pz, H)\n",
ff5df8e3 353 "options(repr.plot.width=9, repr.plot.height=7)\n",
6774e53d 354 "plotError(list(e_nn, e_pz, e_az, e_nn2), cols=c(1,2,colors()[258], 4))\n",
ff5df8e3 355 "\n",
6774e53d 356 "# Noir: Neighbors, bleu: Neighbors2, vert: moyenne, rouge: persistence\n",
ff5df8e3 357 "\n",
6774e53d
BA
358 "i_np = which.min(e_nn$abs$indices)\n",
359 "i_p = which.max(e_nn$abs$indices)"
ff5df8e3
BA
360 ]
361 },
362 {
363 "cell_type": "code",
364 "execution_count": null,
83a13103 365 "metadata": {},
ff5df8e3
BA
366 "outputs": [],
367 "source": [
368 "options(repr.plot.width=9, repr.plot.height=4)\n",
369 "par(mfrow=c(1,2))\n",
370 "\n",
6774e53d
BA
371 "plotPredReal(data, p_nn, i_np); title(paste(\"PredReal nn day\",i_np))\n",
372 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn day\",i_p))\n",
ff5df8e3 373 "\n",
6774e53d
BA
374 "plotPredReal(data, p_nn2, i_np); title(paste(\"PredReal nn2 day\",i_np))\n",
375 "plotPredReal(data, p_nn2, i_p); title(paste(\"PredReal nn2 day\",i_p))\n",
ff5df8e3
BA
376 "\n",
377 "plotPredReal(data, p_az, i_np); title(paste(\"PredReal az day\",i_np))\n",
378 "plotPredReal(data, p_az, i_p); title(paste(\"PredReal az day\",i_p))\n",
379 "\n",
380 "# Bleu: prévue, noir: réalisée"
381 ]
382 },
383 {
384 "cell_type": "code",
385 "execution_count": null,
83a13103 386 "metadata": {},
ff5df8e3
BA
387 "outputs": [],
388 "source": [
389 "par(mfrow=c(1,2))\n",
6774e53d
BA
390 "f_np = computeFilaments(data, p_nn, i_np, plot=TRUE); title(paste(\"Filaments nn day\",i_np))\n",
391 "f_p = computeFilaments(data, p_nn, i_p, plot=TRUE); title(paste(\"Filaments nn day\",i_p))\n",
ff5df8e3 392 "\n",
6774e53d
BA
393 "f_np2 = computeFilaments(data, p_nn2, i_np, plot=TRUE); title(paste(\"Filaments nn2 day\",i_np))\n",
394 "f_p2 = computeFilaments(data, p_nn2, i_p, plot=TRUE); title(paste(\"Filaments nn2 day\",i_p))"
ff5df8e3
BA
395 ]
396 },
397 {
398 "cell_type": "code",
399 "execution_count": null,
83a13103 400 "metadata": {},
ff5df8e3
BA
401 "outputs": [],
402 "source": [
403 "par(mfrow=c(1,2))\n",
6774e53d
BA
404 "plotFilamentsBox(data, f_np); title(paste(\"FilBox nn day\",i_np))\n",
405 "plotFilamentsBox(data, f_p); title(paste(\"FilBox nn day\",i_p))\n",
ff5df8e3 406 "\n",
83a13103
BA
407 "# Generally too few neighbors:\n",
408 "#plotFilamentsBox(data, f_np2); title(paste(\"FilBox nn2 day\",i_np))\n",
409 "#plotFilamentsBox(data, f_p2); title(paste(\"FilBox nn2 day\",i_p))"
ff5df8e3
BA
410 ]
411 },
412 {
413 "cell_type": "code",
414 "execution_count": null,
83a13103 415 "metadata": {},
ff5df8e3
BA
416 "outputs": [],
417 "source": [
418 "par(mfrow=c(1,2))\n",
6774e53d
BA
419 "plotRelVar(data, f_np); title(paste(\"StdDev nn day\",i_np))\n",
420 "plotRelVar(data, f_p); title(paste(\"StdDev nn day\",i_p))\n",
ff5df8e3 421 "\n",
6774e53d
BA
422 "plotRelVar(data, f_np2); title(paste(\"StdDev nn2 day\",i_np))\n",
423 "plotRelVar(data, f_p2); title(paste(\"StdDev nn2 day\",i_p))\n",
ff5df8e3
BA
424 "\n",
425 "# Variabilité globale en rouge ; sur les 60 voisins (+ lendemains) en noir"
426 ]
427 },
428 {
429 "cell_type": "code",
430 "execution_count": null,
83a13103 431 "metadata": {},
ff5df8e3
BA
432 "outputs": [],
433 "source": [
434 "par(mfrow=c(1,2))\n",
6774e53d
BA
435 "plotSimils(p_nn, i_np); title(paste(\"Weights nn day\",i_np))\n",
436 "plotSimils(p_nn, i_p); title(paste(\"Weights nn day\",i_p))\n",
ff5df8e3 437 "\n",
6774e53d
BA
438 "plotSimils(p_nn2, i_np); title(paste(\"Weights nn2 day\",i_np))\n",
439 "plotSimils(p_nn2, i_p); title(paste(\"Weights nn2 day\",i_p))\n",
ff5df8e3
BA
440 "\n",
441 "# - pollué à gauche, + pollué à droite"
442 ]
443 },
444 {
445 "cell_type": "code",
446 "execution_count": null,
83a13103 447 "metadata": {},
ff5df8e3
BA
448 "outputs": [],
449 "source": [
6774e53d
BA
450 "# Fenêtres sélectionnées dans ]0,7] / nn à gauche, nn2 à droite\n",
451 "p_nn$getParams(i_np)$window\n",
452 "p_nn$getParams(i_p)$window\n",
ff5df8e3 453 "\n",
6774e53d
BA
454 "p_nn2$getParams(i_np)$window\n",
455 "p_nn2$getParams(i_p)$window"
ff5df8e3
BA
456 ]
457 }
458 ],
83a13103 459 "metadata": {},
ff5df8e3
BA
460 "nbformat": 4,
461 "nbformat_minor": 2
462}