Small Improvements

Update Notebook_Time_Series_Silviu.ipynb

Update Notebook_Time_Series_Silviu.ipynb

Author: lpinon

Notebook_Time_Series_Silviu.ipynb

@@ -290,7 +290,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def generate_table():    \n",
+    "def init_highest_table():    \n",
     "    df_highest = pd.DataFrame(columns={\"Indicator\"})\n",
     "    df_highest[\"Indicator\"] = indicators\n",
     "    df_highest[\"Year range\"] = 0\n",
@@ -317,22 +317,28 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "iterable = list(range(min(set(df_gold['Year'])), max(set(df_gold['Year'])) + 1))\n",
-    "iterable = list(itertools.combinations(iterable, 2))\n",
-    "iterable_aux = iterable.copy()\n",
-    "\n",
-    "#The year length must be higher than 5. All entries with a lower range are deleted.\n",
-    "for years in iterable_aux:\n",
-    "    if (years[1] - years[0]) < 4:\n",
-    "        iterable.remove(years)\n",
-    "\n",
     "indicators = list(df_gold.columns[3:])\n",
     "indicators.remove('GDP')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_years_combinations(min_diff: int):\n",
+    "    iterable = list(range(min(set(df_gold['Year'])), max(set(df_gold['Year'])) + 1))\n",
+    "    iterable = list(itertools.combinations(iterable, 2))\n",
+    "    \n",
+    "    #The year length must be higher than min_diff. All entries with a lower range are deleted.\n",
+    "    for years in iterable.copy():\n",
+    "        if (years[1] - years[0]) < min_diff:\n",
+    "            iterable.remove(years)\n",
+    "            \n",
+    "    return iterable"
+   ]
+  },
    "metadata": {},
    "outputs": [
     {
@@ -377,17 +383,18 @@
     "        #Search for the entries of the region and normalize.\n",
     "        df_zone = countries_by_region[Zone]\n",
     "\n",
-    "    df_highest = generate_table()\n",
+    "    df_highest = init_highest_table()\n",
     "    \n",
     "    i = 0\n",
     "    computing_text = \"Loading \"\n",
     "    print (computing_text, end=\"\\r\")\n",
     "\n",
     "\n",
     "    #For all the combination of years...\n",
-    "    for years in iterable:\n",
+    "    for years in generate_years_combinations(5):\n",
     "        i = (i + 1) % 50\n",
     "        print (computing_text + \"\".join([\".\" for _ in range(i)]), end=\"\\r\")\n",
+    "        \n",
     "        df_aux = searchTimeSeries(0, years[0], years[1], True, df_zone)\n",
     "        #Delete indicators which are not available that year\n",
     "        indicators_inter = list(set(indicators) & set(list(df_aux.index)))\n",
@@ -476,13 +483,14 @@
     "def plotYearRange(Zone, Indicator, Years):\n",
     "    df_aux = df_gold_index.loc[df_gold_index.index.get_level_values('Country') == Zone]\n",
     "    df_aux = df_aux.loc[(df_aux.index.get_level_values(\"Year\") >= Years[0]) & (df_aux.index.get_level_values(\"Year\") <= Years[1])]\n",
+    "    # TODO: Country or Region??\n",
     "    spear = stats.spearmanr(df_aux[Indicator], df_aux['GDP'])\n",
     "    df_aux = normalize_by_country(df_aux).reset_index(drop=False)\n",
     "    \n",
     "    print(spear)\n",
     "    plt.figure(figsize=(6,6))\n",
-    "    plt.plot(df_aux[\"GDP\"], color=\"red\", label = 'GDP')\n",
-    "    plt.plot(df_aux[Indicator], color=\"green\", label = Indicator)\n",
+    "    plt.plot(df_aux[\"Year\"], df_aux[\"GDP\"], color=\"red\", label = 'GDP')\n",
+    "    plt.plot(df_aux[\"Year\"], df_aux[Indicator], color=\"green\", label = Indicator)\n",
     "    plt.legend(loc=\"lower right\")\n",
     "    \n",
     "\n",
@@ -509,7 +517,6 @@
     ")\n",
     "\n",
     "\n",
-    "\n",
     "# TODO By Region: Say Y axis is Qualitative (Not real values but Normalized to observe evolution vs GDP - Tendendency)\n",
     "widgets.interact(plotYearRange, Zone = country_drop, Indicator = indicator_drop, Years = intslider)"
    ]