final report average 7h; TODO: others

diff --git a/reports/report_2017-03-01.7h_average.ipynb b/reports/report_2017-03-01.7h_average.ipynb
index 6296e29..5da76eb 100644 (file)
--- a/reports/report_2017-03-01.7h_average.ipynb
+++ b/reports/report_2017-03-01.7h_average.ipynb
@@ -50,11 +50,11 @@
    },
    "outputs": [],
    "source": [
    },
    "outputs": [],
    "source": [

-    "indices = seq(as.Date(\"2015-01-18\"),as.Date(\"2015-01-24\"),\"days\")\n",
-    "p_ch_nn = getForecast(data,indices,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
-    "p_ch_pz = getForecast(data, indices, \"Persistence\", \"Zero\", same_day=TRUE)\n",
-    "p_ch_az = getForecast(data, indices, \"Average\", \"Zero\") #, memory=183)\n",
-    "#p_ch_zz = getForecast(data, indices, \"Zero\", \"Zero\")"
+    "indices_ch = seq(as.Date(\"2015-01-18\"),as.Date(\"2015-01-24\"),\"days\")\n",
+    "p_ch_nn = getForecast(data,indices_ch,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
+    "p_ch_pz = getForecast(data, indices_ch, \"Persistence\", \"Zero\", same_day=TRUE)\n",
+    "p_ch_az = getForecast(data, indices_ch, \"Average\", \"Zero\") #, memory=183)\n",
+    "#p_ch_zz = getForecast(data, indices_ch, \"Zero\", \"Zero\")"

    ]
   },
   {
    ]
   },
   {


@@ -134,8 +134,8 @@
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",

-    "f3 = computeFilaments(data, p_ch_nn$getIndexInData(3), plot=TRUE)\n",
-    "f4 = computeFilaments(data, p_ch_nn$getIndexInData(4), plot=TRUE)"
+    "f3_ch = computeFilaments(data, p_ch_nn$getIndexInData(3), plot=TRUE)\n",
+    "f4_ch = computeFilaments(data, p_ch_nn$getIndexInData(4), plot=TRUE)"

    ]
   },
   {
    ]
   },
   {


@@ -148,10 +148,10 @@
    "source": [
     "par(mfrow=c(2,2))\n",
     "options(repr.plot.width=9, repr.plot.height=7)\n",
    "source": [
     "par(mfrow=c(2,2))\n",
     "options(repr.plot.width=9, repr.plot.height=7)\n",

-    "plotFilamentsBox(data, f3$indices)\n",
-    "plotFilamentsBox(data, f3$indices+1)\n",
-    "plotFilamentsBox(data, f4$indices)\n",
-    "plotFilamentsBox(data, f4$indices+1)\n",
+    "plotFilamentsBox(data, f3_ch$indices)\n",
+    "plotFilamentsBox(data, f3_ch$indices+1)\n",
+    "plotFilamentsBox(data, f4_ch$indices)\n",
+    "plotFilamentsBox(data, f4_ch$indices+1)\n",

     "\n",
     "#En haut : jour 3 + lendemain (4) ; en bas : jour 4 + lendemain (5)\n",
     "#À gauche : premières 24h ; à droite : 24h suivantes"
     "\n",
     "#En haut : jour 3 + lendemain (4) ; en bas : jour 4 + lendemain (5)\n",
     "#À gauche : premières 24h ; à droite : 24h suivantes"


@@ -174,8 +174,8 @@
    "source": [
     "par(mfrow=c(1,2))\n",
     "options(repr.plot.width=9, repr.plot.height=4)\n",
    "source": [
     "par(mfrow=c(1,2))\n",
     "options(repr.plot.width=9, repr.plot.height=4)\n",

-    "plotRelativeVariability(data, f3$indices)\n",
-    "plotRelativeVariability(data, f4$indices)\n",
+    "plotRelativeVariability(data, f3_ch$indices)\n",
+    "plotRelativeVariability(data, f4_ch$indices)\n",

     "\n",
     "#Variabilité sur 60 courbes au hasard en rouge ; sur nos 60 voisins (+ lendemains) en noir"
    ]
     "\n",
     "#Variabilité sur 60 courbes au hasard en rouge ; sur nos 60 voisins (+ lendemains) en noir"
    ]


@@ -238,11 +238,11 @@
    },
    "outputs": [],
    "source": [
    },
    "outputs": [],
    "source": [

-    "indices = seq(as.Date(\"2015-03-15\"),as.Date(\"2015-03-21\"),\"days\")\n",
-    "p_ep_nn = getForecast(data,indices,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
-    "p_ep_pz = getForecast(data, indices, \"Persistence\", \"Zero\", same_day=TRUE)\n",
-    "p_ep_az = getForecast(data, indices, \"Average\", \"Zero\") #, memory=183)\n",
-    "#p_ep_zz = getForecast(data, indices, \"Zero\", \"Zero\")"
+    "indices_ep = seq(as.Date(\"2015-03-15\"),as.Date(\"2015-03-21\"),\"days\")\n",
+    "p_ep_nn = getForecast(data,indices_ep,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
+    "p_ep_pz = getForecast(data, indices_ep, \"Persistence\", \"Zero\", same_day=TRUE)\n",
+    "p_ep_az = getForecast(data, indices_ep, \"Average\", \"Zero\") #, memory=183)\n",
+    "#p_ep_zz = getForecast(data, indices_ep, \"Zero\", \"Zero\")"

    ]
   },
   {
    ]
   },
   {


@@ -257,7 +257,6 @@
     "e_ep_pz = getError(data, p_ep_pz)\n",
     "e_ep_az = getError(data, p_ep_az)\n",
     "#e_ep_zz = getError(data, p_ep_zz)\n",
     "e_ep_pz = getError(data, p_ep_pz)\n",
     "e_ep_az = getError(data, p_ep_az)\n",
     "#e_ep_zz = getError(data, p_ep_zz)\n",

-    "#e_ep_l = getError(data, p_ep_l)\n",

     "options(repr.plot.width=9, repr.plot.height=7)\n",
     "plotError(list(e_ep_nn, e_ep_pz, e_ep_az), cols=c(1,2,colors()[258]))\n",
     "\n",
     "options(repr.plot.width=9, repr.plot.height=7)\n",
     "plotError(list(e_ep_nn, e_ep_pz, e_ep_az), cols=c(1,2,colors()[258]))\n",
     "\n",


@@ -281,8 +280,8 @@
    "source": [
     "par(mfrow=c(1,2))\n",
     "options(repr.plot.width=9, repr.plot.height=4)\n",
    "source": [
     "par(mfrow=c(1,2))\n",
     "options(repr.plot.width=9, repr.plot.height=4)\n",

-    "plotPredReal(data, p_ep_nn, 5)\n",
-    "plotPredReal(data, p_ep_nn, 2)\n",
+    "plotPredReal(data, p_ep_nn, 4)\n",
+    "plotPredReal(data, p_ep_nn, 6)\n",

     "\n",
     "#Bleu: prévue, noir: réalisée"
    ]
     "\n",
     "#Bleu: prévue, noir: réalisée"
    ]


@@ -311,7 +310,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
    "cell_type": "markdown",
    "metadata": {},
    "source": [

-    "Bonnes performances de la persistence (par chance...)"
+    "Assez bonnes performances de la persistence (par chance...)"

    ]
   },
   {
    ]
   },
   {


@@ -323,8 +322,34 @@
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",

-    "plotFilaments(data, p_ep_nn$getIndexInData(5))\n",
-    "plotFilaments(data, p_ep_nn$getIndexInData(2))"
+    "f4_ep = computeFilaments(data, p_ep_nn$getIndexInData(4), plot=TRUE)\n",
+    "f6_ep = computeFilaments(data, p_ep_nn$getIndexInData(6), plot=TRUE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "par(mfrow=c(2,2))\n",
+    "options(repr.plot.width=9, repr.plot.height=7)\n",
+    "plotFilamentsBox(data, f4_ep$indices)\n",
+    "plotFilamentsBox(data, f4_ep$indices+1)\n",
+    "plotFilamentsBox(data, f6_ep$indices)\n",
+    "plotFilamentsBox(data, f6_ep$indices+1)\n",
+    "\n",
+    "#En haut : jour 4 + lendemain (5) ; en bas : jour 6 + lendemain (7)\n",
+    "#À gauche : premières 24h ; à droite : 24h suivantes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\"Voisinages\" catastrophiques : les jours 4 et 6 sont trop atypiques ; de façon étonnante les lendemains sont en revanche assez \"centraux\" parmi les lendemains des (mauvais) voisins."

    ]
   },
   {
    ]
   },
   {


@@ -336,22 +361,45 @@
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",

-    "plotSimils(p_ep_nn, 5)\n",
-    "plotSimils(p_ep_nn, 2)"
+    "options(repr.plot.width=9, repr.plot.height=4)\n",
+    "plotRelativeVariability(data, f4_ep$indices)\n",
+    "plotRelativeVariability(data, f6_ep$indices)\n",
+    "\n",
+    "#Variabilité sur 60 courbes au hasard en rouge ; sur nos 60 voisins (+ lendemains) en noir"

    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [

-    "Même observation concernant les poids : concentrés près de zéro pour les prédictions avec peu de voisins."
+    "Dans la situation idéale, il faudrait que la courbe noire soit nettement plus basse que la courbe rouge. Ce n'est pas vérifié à J+1, sauf pour le jour 6 en début et fin de journée."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "par(mfrow=c(1,2))\n",
+    "plotSimils(p_ep_nn, 4)\n",
+    "plotSimils(p_ep_nn, 6)"

    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [

-    "## Semaine non polluée"
+    "Poids très concentrés près de zéro pour les prédictions avec peu de voisins."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<h2 style=\"color:blue;font-size:2em\">Semaine non polluée</h2>"

    ]
   },
   {
    ]
   },
   {


@@ -362,12 +410,11 @@
    },
    "outputs": [],
    "source": [
    },
    "outputs": [],
    "source": [

-    "indices = seq(as.Date(\"2015-04-26\"),as.Date(\"2015-05-02\"),\"days\")\n",
-    "p_np_nn = getForecast(data,indices,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
-    "p_np_pz = getForecast(data, indices, \"Persistence\", \"Zero\", same_day=FALSE)\n",
-    "p_np_az = getForecast(data, indices, \"Average\", \"Zero\") #, memory=183)\n",
-    "#p_np_zz = getForecast(data, indices, \"Zero\", \"Zero\")\n",
-    "#p_np_l = getForecast(data, indices, \"Level\", same_day=FALSE)"
+    "indices_np = seq(as.Date(\"2015-04-26\"),as.Date(\"2015-05-02\"),\"days\")\n",
+    "p_np_nn = getForecast(data,indices_np,\"Neighbors\",\"Neighbors\",simtype=\"mix\",same_season=FALSE,mix_strategy=\"mult\")\n",
+    "p_np_pz = getForecast(data, indices_np, \"Persistence\", \"Zero\", same_day=FALSE)\n",
+    "p_np_az = getForecast(data, indices_np, \"Average\", \"Zero\") #, memory=183)\n",
+    "#p_np_zz = getForecast(data, indices_np, \"Zero\", \"Zero\")"

    ]
   },
   {
    ]
   },
   {


@@ -382,8 +429,7 @@
     "e_np_pz = getError(data, p_np_pz)\n",
     "e_np_az = getError(data, p_np_az)\n",
     "#e_np_zz = getError(data, p_np_zz)\n",
     "e_np_pz = getError(data, p_np_pz)\n",
     "e_np_az = getError(data, p_np_az)\n",
     "#e_np_zz = getError(data, p_np_zz)\n",

-    "#e_np_l = getError(data, p_np_l)\n",
-    "options(repr.plot.width=9, repr.plot.height=6)\n",
+    "options(repr.plot.width=9, repr.plot.height=7)\n",

     "plotError(list(e_np_nn, e_np_pz, e_np_az), cols=c(1,2,colors()[258]))\n",
     "\n",
     "#Noir: neighbors, rouge: persistence, vert: moyenne"
     "plotError(list(e_np_nn, e_np_pz, e_np_az), cols=c(1,2,colors()[258]))\n",
     "\n",
     "#Noir: neighbors, rouge: persistence, vert: moyenne"


@@ -436,7 +482,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
    "cell_type": "markdown",
    "metadata": {},
    "source": [

-    "Légèrement meilleur ajustement par la méthode \"Average\" ; très net à droite."
+    "Légèrement meilleur ajustement par la méthode \"Average\" ; plutôt net à droite."

    ]
   },
   {
    ]
   },
   {


@@ -448,15 +494,57 @@
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",
    "outputs": [],
    "source": [
     "par(mfrow=c(1,2))\n",

-    "plotFilaments(data, p_np_nn$getIndexInData(3))\n",
-    "plotFilaments(data, p_np_nn$getIndexInData(6))"
+    "f3_np = computeFilaments(data, p_np_nn$getIndexInData(3), plot=TRUE)\n",
+    "f6_np = computeFilaments(data, p_np_nn$getIndexInData(6), plot=TRUE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "par(mfrow=c(2,2))\n",
+    "options(repr.plot.width=9, repr.plot.height=7)\n",
+    "plotFilamentsBox(data, f3_np$indices)\n",
+    "plotFilamentsBox(data, f3_np$indices+1)\n",
+    "plotFilamentsBox(data, f6_np$indices)\n",
+    "plotFilamentsBox(data, f6_np$indices+1)\n",
+    "\n",
+    "#En haut : jour 3 + lendemain (4) ; en bas : jour 6 + lendemain (7)\n",
+    "#À gauche : premières 24h ; à droite : 24h suivantes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Jours \"typiques\", donc beaucoup de voisins. En revanche les lendemains des jours similaires sont très variables."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "par(mfrow=c(1,2))\n",
+    "options(repr.plot.width=9, repr.plot.height=4)\n",
+    "plotRelativeVariability(data, f3_np$indices)\n",
+    "plotRelativeVariability(data, f6_np$indices)\n",
+    "\n",
+    "#Variabilité sur 60 courbes au hasard en rouge ; sur nos 60 voisins (+ lendemains) en noir"

    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [

-    "Jours \"typiques\", donc beaucoup de voisins."
+    "Situation quasi-idéale : la courbe noire est toujours assez nettement en dessous."

    ]
   },
   {
    ]
   },
   {