handling nordic (æøå), data cleaning

torave · Mar 30, 2025 · 2d9de07 · 2d9de07
1 parent 704d63f
commit 2d9de07
Showing 1 changed file with 152 additions and 7 deletions.
diff --git a/notebooks/notebook_current_data.ipynb b/notebooks/notebook_current_data.ipynb
@@ -19,9 +19,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data fetch: ok\n"
+     ]
+    }
+   ],
    "source": [
     "import sys\n",
     "import os\n",
@@ -35,6 +43,12 @@
     "# User input the city, for the weather\n",
     "city_name = input(\"Enter a city in Norway: \")\n",
     "\n",
+    "for letter in city_name:\n",
+    "    if letter in 'æøå':\n",
+    "        city_name = city_name.replace('æ', 'ae')\n",
+    "        city_name = city_name.replace('ø', 'o')\n",
+    "        city_name = city_name.replace('å', 'aa')\n",
+    "\n",
     "# Stores the return of the function\n",
     "data, folder = fetch_current_data(city_name)"
    ]
@@ -54,9 +68,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data has been written to /Users/toravestlund/Documents/ITBAITBEDR/TDT4114 - Anvendt programmering/anvendt_mappe/data/../data/output_current_data/data_aaa_maura.json\n"
+     ]
+    }
+   ],
    "source": [
     "# Gets the absolute path to the src folder\n",
     "sys.path.append(os.path.abspath(\"../src\"))\n",
@@ -81,9 +103,44 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'coord': {'lon': 11.0167, 'lat': 60.25},\n",
+       " 'weather': [{'id': 500,\n",
+       "   'main': 'Rain',\n",
+       "   'description': 'light rain',\n",
+       "   'icon': '10d'}],\n",
+       " 'base': 'stations',\n",
+       " 'main': {'temp': 3.14,\n",
+       "  'temp_min': 2.52,\n",
+       "  'temp_max': 3.84,\n",
+       "  'humidity': 93,\n",
+       "  'sea_level': 1003,\n",
+       "  'grnd_level': 965},\n",
+       " 'visibility': 10000,\n",
+       " 'wind': {'speed': 1.54, 'deg': 70},\n",
+       " 'rain': {'1h': 0.11},\n",
+       " 'clouds': {'all': 75},\n",
+       " 'dt': 1743329160,\n",
+       " 'sys': {'type': 1,\n",
+       "  'id': 1624,\n",
+       "  'country': 'NO',\n",
+       "  'sunrise': 1743309996,\n",
+       "  'sunset': 1743357233},\n",
+       " 'timezone': 7200,\n",
+       " 'id': 3146270,\n",
+       " 'name': 'Maura',\n",
+       " 'cod': 200}"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import json\n",
     "\n",
@@ -118,7 +175,92 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>name</th>\n",
+       "      <th>main.temp</th>\n",
+       "      <th>main.humidity</th>\n",
+       "      <th>main.sea_level</th>\n",
+       "      <th>main.grnd_level</th>\n",
+       "      <th>wind.speed</th>\n",
+       "      <th>rain.1h</th>\n",
+       "      <th>clouds.all</th>\n",
+       "      <th>sys.country</th>\n",
+       "      <th>sys.sunrise</th>\n",
+       "      <th>sys.sunset</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>dt</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2025-03-30 10:06:00</th>\n",
+       "      <td>Maura</td>\n",
+       "      <td>3.14</td>\n",
+       "      <td>93</td>\n",
+       "      <td>1003</td>\n",
+       "      <td>965</td>\n",
+       "      <td>1.54</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>75</td>\n",
+       "      <td>NO</td>\n",
+       "      <td>2025-03-30 04:46:36</td>\n",
+       "      <td>2025-03-30 17:53:53</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      name  main.temp  main.humidity  main.sea_level  \\\n",
+       "dt                                                                     \n",
+       "2025-03-30 10:06:00  Maura       3.14             93            1003   \n",
+       "\n",
+       "                     main.grnd_level  wind.speed  rain.1h  clouds.all  \\\n",
+       "dt                                                                      \n",
+       "2025-03-30 10:06:00              965        1.54     0.11          75   \n",
+       "\n",
+       "                    sys.country         sys.sunrise          sys.sunset  \n",
+       "dt                                                                       \n",
+       "2025-03-30 10:06:00          NO 2025-03-30 04:46:36 2025-03-30 17:53:53  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import pandas as pd\n",
     "\n",
@@ -151,6 +293,9 @@
     "df['dt'] = pd.to_datetime(df['dt'], unit='s')\n",
     "df.set_index('dt', inplace=True)\n",
     "\n",
+    "# Drops the whole column, if all values is 'NaN' value.\n",
+    "df = df.dropna(axis='columns', how='all')\n",
+    "\n",
     "# Display the df after changes\n",
     "display(df)"
    ]