From 704d63ffd053b409b377ebb3dba3176d5141497b Mon Sep 17 00:00:00 2001
From: toravest <torave@stud.ntnu.no>
Date: Sun, 30 Mar 2025 12:29:31 +0200
Subject: [PATCH] rename notebook, check outliers, missing data (data cleaning)

---
 notebooks/notebook_statistic_data.ipynb | 581 ++++++++++++++++++++++++
 notebooks/statistic_data_notebook.ipynb | 180 --------
 2 files changed, 581 insertions(+), 180 deletions(-)
 create mode 100644 notebooks/notebook_statistic_data.ipynb
 delete mode 100644 notebooks/statistic_data_notebook.ipynb

diff --git a/notebooks/notebook_statistic_data.ipynb b/notebooks/notebook_statistic_data.ipynb
new file mode 100644
index 0000000..836d891
--- /dev/null
+++ b/notebooks/notebook_statistic_data.ipynb
@@ -0,0 +1,581 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Notebook - Statistic data\n",
+    "Denne notebooken henter data fra en API som samler alle historiske data for ønsket sted, å regner ut statistiske verdier for alle dagene i året. Vi fjerner uønskede kolonner, utelukker ekstremverdier og visualiserer data gjennom plotter. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Velg et sted i Norge å få statistisk data\n",
+    "\n",
+    "Denne API-en henter statistisk historisk data, herunder, statistisk data basert på de historiske dataene, ikke reele statistisk historisk. \n",
+    "\n",
+    "Statistikken er basert på de historiske datane total sett, ikke for hvert år."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "\n",
+    "# Gets the absolute path to the src folder\n",
+    "sys.path.append(os.path.abspath(\"../src\"))\n",
+    "\n",
+    "# Now we can import the fucntion from the module\n",
+    "from my_package.year_data import fetch_data\n",
+    "\n",
+    "# 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",
+    "data, folder = fetch_data(city_name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Lagre data i json-fil\n",
+    "\n",
+    "Skriv inn navn for til filen du vil lagre med dataen.\n",
+    "\n",
+    "Eks. test\n",
+    "Da vil filen lagres som data_**test**.json, i mappen \"../data/output_statistikk/data_{filnavn}.json\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Gets the absolute path to the src folder\n",
+    "sys.path.append(os.path.abspath(\"../src\"))\n",
+    "\n",
+    "from my_package.write_data import write_data\n",
+    "\n",
+    "filename = input(\"Write filename: \")\n",
+    "\n",
+    "write_data(data, folder, filename)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Lese fra fil\n",
+    "\n",
+    "Henter opp data lagret i filen over, og lagrer i en variabel."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "data = pd.read_json(f'../data/output_statistikk/data_{filename}.json')\n",
+    "\n",
+    "# Display data\n",
+    "display(data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Lesbar data\n",
+    "Sørger for at dataen lagret over blir mer lesbar."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "# Checks if the 'result' column is in the data\n",
+    "if 'result' in data:\n",
+    "    # Normalize the json and store it as a dataframe for better readability\n",
+    "    df = pd.json_normalize(data['result'])\n",
+    "\n",
+    "    # Display the dataframe\n",
+    "    display(df)\n",
+    "else:\n",
+    "    print(\"'result' not in data\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Rydder i data\n",
+    "Fjerner alle kolonner vi ikke trenger, som standardavvik for alle kategorier for alle dager, vi kan regne ut en felles ved å bruke statistisc modulen. \n",
+    "\n",
+    "Ettersom alle kateogirene har lik data, ogg vi vil fjerne noen av verdiene fra alle kategoriene. Kan vi bruke filter funksjonen til å filtrere ut dataene som inneholder f.eks. '.st_dev'. Dette gjør at alle kategoirene fjernes på likt å vi slipper å skrive alle flere ganger."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Drop all columns that end with '...' using the filter function\n",
+    "df = df.drop(columns=df.filter(like='.p25').columns)\n",
+    "df = df.drop(columns=df.filter(like='.p75').columns)\n",
+    "df = df.drop(columns=df.filter(like='.st_dev').columns)\n",
+    "df = df.drop(columns=df.filter(like='.num').columns)\n",
+    "\n",
+    "display(df)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Plotter temperatur\n",
+    "Denne koden plotter data basert på gjennomsnitts temperatur gjennom året. For å sikre lagring av de ulike kjøringene, vil grafen bli lagret i mappen \"../data/output_fig/mean_temp_plot_{city_name}.json\"\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.dates as mdates\n",
+    "import os\n",
+    "\n",
+    "output_folder = \"../data/output_fig\"\n",
+    "os.makedirs(output_folder, exist_ok=True)  # Create the folder if it doesn't exist\n",
+    "\n",
+    "# Converts to and make a new column with celsius temp, and not kelvin\n",
+    "df['temp.mean_celsius'] = df['temp.mean'] - 272.15\n",
+    "temp = df['temp.mean_celsius']\n",
+    "\n",
+    "# Convert from day and month, to datetime\n",
+    "# df['date'] = pd.to_datetime(df[['month', 'day']].assign(year=2024))\n",
+    "\n",
+    "# Create a new column that concatenates month and day (e.g., \"03-01\" for March 1)\n",
+    "df['month_day'] = df[['month', 'day']].apply(lambda x: f\"{x['month']:02d}-{x['day']:02d}\",axis=1)\n",
+    "\n",
+    "# Plot the graph of the mean temperature\n",
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.plot(df['month_day'], temp)\n",
+    "\n",
+    "# Label for easier reading and understanding of the plot\n",
+    "plt.title(f\"Mean temp - statistic historical {city_name}\")\n",
+    "plt.xlabel(\"Date\")\n",
+    "plt.ylabel(\"Temperature (°C)\")\n",
+    "\n",
+    "# Customize the x-axis to show ticks and labels only at the start of each month\n",
+    "plt.gca().xaxis.set_major_locator(mdates.MonthLocator())  \n",
+    "# Format ticks to show abbreviated month names (e.g., Jan, Feb)\n",
+    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b')) \n",
+    "\n",
+    "plt.xticks(rotation=45)\n",
+    "plt.yticks(range(-20, 30, 2))\n",
+    "plt.tight_layout()\n",
+    "plt.grid()\n",
+    "\n",
+    "# Save the plot to the data/output_fig folder\n",
+    "plot_path = os.path.join(output_folder, f\"mean_temp_plot_{city_name}.png\")\n",
+    "plt.savefig(plot_path)  # Save the plot as a PNG file\n",
+    "\n",
+    "# Show the plot\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Plotter data\n",
+    "Her plottes temperatur og regn på samme akse, med vind i en egen graf under, men de deler samme x-akse, som er month_date."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.dates as mdates\n",
+    "import os\n",
+    "\n",
+    "# Defines the output folder for the figure, and makes it if is does not exsist\n",
+    "output_folder = \"../data/output_fig\"\n",
+    "os.makedirs(output_folder, exist_ok=True)  \n",
+    "\n",
+    "# Converts to and make a new column with celsius temp, and not kelvin\n",
+    "df['temp.mean_celsius'] = df['temp.mean'] - 272.15\n",
+    "temp = df['temp.mean_celsius']\n",
+    "precipitation = df['precipitation.mean']\n",
+    "wind = df['wind.mean']\n",
+    "\n",
+    "# Create a new column that concatenates month and day (e.g., \"03-01\" for March 1)\n",
+    "df['month_day'] = df[['month', 'day']].apply(lambda x: f\"{x['month']:02d}-{x['day']:02d}\",axis=1)\n",
+    "\n",
+    "x_axis = df['month_day']\n",
+    "\n",
+    "fig, (ax1, ax3) = plt.subplots(2, 1, figsize = (15, 8), sharex=True)\n",
+    "\n",
+    "# Plot temperature on the primary y-axis\n",
+    "ax1.plot(x_axis, temp, color='tab:red', label='Temperature (°C)')\n",
+    "# ax1.set_xlabel('Datetime')\n",
+    "ax1.set_ylabel('Temperature (°C)', color='tab:red')\n",
+    "ax1.tick_params(axis='y', labelcolor='tab:red')\n",
+    "\n",
+    "# Plot precipitation as bars on the secondary y-axis\n",
+    "ax2 = ax1.twinx()\n",
+    "ax2.bar(x_axis, precipitation, color='tab:blue', alpha=0.5, width=1, label='Precipitation (mm)')\n",
+    "ax2.set_ylabel(\"Precipitation (mm)\", color='tab:blue')\n",
+    "ax2.tick_params(axis='y', labelcolor='tab:blue')\n",
+    "\n",
+    "ax1.grid(axis = 'x')\n",
+    "ax1.legend(loc='upper left')\n",
+    "ax2.legend(loc='upper right')\n",
+    "\n",
+    "ax3.plot(x_axis, wind, color='tab:purple', label='Wind (m/s)')\n",
+    "# ax3.plot(x_axis, wind_speed, color='tab:purple', linestyle='dashed', label='Wind_speed')\n",
+    "ax3.set_ylabel('Wind (m/s)')\n",
+    "ax3.set_xlabel('Datetime')\n",
+    "ax3.legend(loc='upper right')\n",
+    "\n",
+    "ax3.grid(axis = 'x')\n",
+    "\n",
+    "\n",
+    "# Customize the x-axis to show ticks and labels only at the start of each month\n",
+    "plt.gca().xaxis.set_major_locator(mdates.MonthLocator())  \n",
+    "# Format ticks to show abbreviated month names (e.g., Jan, Feb)\n",
+    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b')) \n",
+    "\n",
+    "plt.tight_layout()\n",
+    "\n",
+    "# Show the plot\n",
+    "plt.show()\n",
+    "\n",
+    "print(df['precipitation.max'].max())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Visualiserer målte tempraturer\n",
+    "\n",
+    "Ved hjelp av matplotlib visualiserer vi temperaturen målt for alle dagene.\n",
+    "\n",
+    "Forklaring til grafen:\n",
+    "- Grå graf: gjennomsnitt av alle målingene\n",
+    "- Rød graf: høyeste målte temperatur\n",
+    "- Blå graf: laveste målte temperatur"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.dates as mdates\n",
+    "\n",
+    "# Converts to and make a new column with celsius temp, and not kelvin\n",
+    "df['temp.mean_celsius'] = df['temp.mean'] - 272.15\n",
+    "temp_mean = df['temp.mean_celsius']\n",
+    "\n",
+    "df['temp.record_max_celsius'] = df['temp.record_max'] - 272.15\n",
+    "temp_record_max = df['temp.record_max_celsius']\n",
+    "\n",
+    "df['temp.record_min_celsius'] = df['temp.record_min'] - 272.15\n",
+    "temp_record_min = df['temp.record_min_celsius']\n",
+    "\n",
+    "# Create a new column that concatenates month and day (e.g., \"03-01\" for March 1)\n",
+    "df['month_day'] = df[['month', 'day']].apply(lambda x: f\"{x['month']:02d}-{x['day']:02d}\",axis=1)\n",
+    "\n",
+    "# Set the month_date as values for the x_axis\n",
+    "x_axis = df['month_day']\n",
+    "\n",
+    "# Defines the height and width of the figure\n",
+    "plt.figure(figsize=(12, 6))\n",
+    "\n",
+    "# Plots the temperatur\n",
+    "plt.plot(x_axis, temp_mean, color='tab:gray', label='Mean temperatur')\n",
+    "plt.plot(x_axis, temp_record_max, color='tab:red', label = 'Max temperatur')\n",
+    "plt.plot(x_axis, temp_record_min, color='tab:blue', label = 'Min temperatur')\n",
+    "\n",
+    "\n",
+    "# Customize the x-axis to show ticks and labels only at the start of each month\n",
+    "plt.gca().xaxis.set_major_locator(mdates.MonthLocator())  \n",
+    "# Format ticks to show abbreviated month names (e.g., Jan, Feb)\n",
+    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b')) \n",
+    "\n",
+    "plt.tight_layout()\n",
+    "\n",
+    "# Plot title with city_name\n",
+    "plt.title(f'Temperatur {city_name}')\n",
+    "\n",
+    "# Add grid\n",
+    "plt.grid()\n",
+    "\n",
+    "# Show the label description\n",
+    "plt.legend(loc = 'upper right')\n",
+    "\n",
+    "# Show the plot\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sjekker uteliggere\n",
+    "Denne koden sjekker om det er noen uteliggere i de ulike temperatur grafene, altså om noen verdier ligger mer enn 3 standardavvik i fra gjennomsnittet."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import statistics\n",
+    "\n",
+    "# Ensure 'month_day' is set as the index\n",
+    "if 'month_day' in df.columns:\n",
+    "    df.set_index('month_day', inplace=True)\n",
+    "else:\n",
+    "    print('month_day not in')\n",
+    "\n",
+    "# Extract temperature columns\n",
+    "temp_mean = df['temp.mean_celsius']\n",
+    "temp_record_min = df['temp.record_min_celsius']\n",
+    "temp_record_max = df['temp.record_max_celsius']\n",
+    "\n",
+    "# Calculate means\n",
+    "temp_mean_mean = temp_mean.mean()\n",
+    "temp_record_min_mean = temp_record_min.mean()\n",
+    "temp_record_max_mean = temp_record_max.mean()\n",
+    "\n",
+    "# Calculate standard deviations\n",
+    "temp_mean_stdev = statistics.stdev(temp_mean)\n",
+    "temp_record_min_stdev = statistics.stdev(temp_record_min)\n",
+    "temp_record_max_stdev = statistics.stdev(temp_record_max)\n",
+    "\n",
+    "# Calculate 3 standard deviation limits\n",
+    "mean_lower_limit = temp_mean_mean - (temp_mean_stdev * 3)\n",
+    "mean_upper_limit = temp_mean_mean + (temp_mean_stdev * 3)\n",
+    "\n",
+    "min_lower_limit = temp_record_min_mean - (temp_record_min_stdev * 3)\n",
+    "min_upper_limit = temp_record_min_mean + (temp_record_min_stdev * 3)\n",
+    "\n",
+    "max_lower_limit = temp_record_max_mean - (temp_record_max_stdev * 3)\n",
+    "max_upper_limit = temp_record_max_mean + (temp_record_max_stdev * 3)\n",
+    "\n",
+    "# Identify outliers\n",
+    "mean_outliers = df.loc[(df['temp.mean_celsius'] > mean_upper_limit) | (df['temp.mean_celsius'] < mean_lower_limit), 'temp.mean_celsius']\n",
+    "min_outliers = df.loc[(df['temp.record_min_celsius'] > min_upper_limit) | (df['temp.record_min_celsius'] < min_lower_limit), 'temp.record_min_celsius']\n",
+    "max_outliers = df.loc[(df['temp.record_max_celsius'] > max_upper_limit) | (df['temp.record_max_celsius'] < max_lower_limit), 'temp.record_max_celsius']\n",
+    "\n",
+    "# Print the outliers\n",
+    "print(\"Outliers in temp.mean_celsius:\")\n",
+    "print(mean_outliers)\n",
+    "\n",
+    "print(\"Outliers in temp.record_min_celsius:\")\n",
+    "print(min_outliers)\n",
+    "\n",
+    "print(\"Outliers in temp.record_max_celsius:\")\n",
+    "print(max_outliers)\n",
+    "\n",
+    "# Replace outliers with NaN\n",
+    "df.loc[(df['temp.mean_celsius'] > mean_upper_limit) | (df['temp.mean_celsius'] < mean_lower_limit), 'temp.mean_celsius'] = np.nan\n",
+    "df.loc[(df['temp.record_min_celsius'] > min_upper_limit) | (df['temp.record_min_celsius'] < min_lower_limit), 'temp.record_min_celsius'] = np.nan\n",
+    "df.loc[(df['temp.record_max_celsius'] > max_upper_limit) | (df['temp.record_max_celsius'] < max_lower_limit), 'temp.record_max_celsius'] = np.nan\n",
+    "\n",
+    "# Interpolate to replace NaN values with linear interpolation\n",
+    "df['temp.mean_celsius'] = df['temp.mean_celsius'].interpolate(method='linear')\n",
+    "df['temp.record_min_celsius'] = df['temp.record_min_celsius'].interpolate(method='linear')\n",
+    "df['temp.record_max_celsius'] = df['temp.record_max_celsius'].interpolate(method='linear')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Visualiserer temperatur etter endringer\n",
+    "Hvis det er uteliggere i dataen, som skal ha blitt endret, vil denne plotten vise en mer riktig og \"feilfri\" plot."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.dates as mdates\n",
+    "\n",
+    "# Ensure 'month_day' is set as the index for proper plotting\n",
+    "if 'month_day' in df.columns:\n",
+    "    df.set_index('month_day', inplace=True)\n",
+    "\n",
+    "# Extract updated temperature columns\n",
+    "temp_mean = df['temp.mean_celsius']\n",
+    "temp_record_max = df['temp.record_max_celsius']\n",
+    "temp_record_min = df['temp.record_min_celsius']\n",
+    "\n",
+    "# Plot the updated temperature data\n",
+    "plt.figure(figsize=(12, 6))\n",
+    "\n",
+    "# Plot mean, max, and min temperatures\n",
+    "plt.plot(temp_mean.index, temp_mean, color='tab:gray', label='Mean Temperature')\n",
+    "plt.plot(temp_record_max.index, temp_record_max, color='tab:red', label='Max Temperature')\n",
+    "plt.plot(temp_record_min.index, temp_record_min, color='tab:blue', label='Min Temperature')\n",
+    "\n",
+    "# Customize the x-axis to show ticks and labels only at the start of each month\n",
+    "plt.gca().xaxis.set_major_locator(mdates.MonthLocator())  \n",
+    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b'))  # Format ticks to show abbreviated month names (e.g., Jan, Feb)\n",
+    "\n",
+    "# Add labels, title, and legend\n",
+    "plt.xlabel('Month-Day')\n",
+    "plt.ylabel('Temperature (°C)')\n",
+    "plt.title(f'Temperature Data for {city_name}')\n",
+    "plt.legend(loc='upper right')\n",
+    "\n",
+    "# Add grid for better readability\n",
+    "plt.grid()\n",
+    "\n",
+    "# Adjust layout to prevent overlap\n",
+    "plt.tight_layout()\n",
+    "\n",
+    "# Show the plot\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Rekorder\n",
+    "\n",
+    "Denne funksjonen regner ut ulike rekorder for året, for angitt sted."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "\n",
+    "# Gets the absolute path to the src folder\n",
+    "sys.path.append(os.path.abspath(\"../src\"))\n",
+    "\n",
+    "from my_package.get_record import get_records\n",
+    "\n",
+    "summary_df, filename, folder = get_records(df, city_name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Skriver dataen til fil\n",
+    "Lagrer rekord-dataen i en fil, med stedsnavn."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Gets the absolute path to the src folder\n",
+    "sys.path.append(os.path.abspath(\"../src\"))\n",
+    "\n",
+    "from my_package.write_data import write_data\n",
+    "# makes the data 'json-compatible'\n",
+    "json_data = summary_df.to_dict(orient=\"records\")\n",
+    "\n",
+    "write_data(json_data, folder, filename)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Leser fra fil, og printer data\n",
+    "Denne funksjonen henter rekordene fra filen den ble skrevet til, og displayer de som en fin lettlest tabell."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import json\n",
+    "\n",
+    "# Reads data from file and store it\n",
+    "with open(f\"../data/output_record/data_{filename}.json\", \"r\", encoding=\"utf-8\") as file:\n",
+    "    data = json.load(file)\n",
+    "\n",
+    "# Normalize the data for better readability\n",
+    "df = pd.json_normalize(data)\n",
+    "\n",
+    "\n",
+    "# Displays the dataframe\n",
+    "display(df)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/notebooks/statistic_data_notebook.ipynb b/notebooks/statistic_data_notebook.ipynb
deleted file mode 100644
index e4b10d1..0000000
--- a/notebooks/statistic_data_notebook.ipynb
+++ /dev/null
@@ -1,180 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Velg et sted i Norge å få statistisk data\n",
-    "\n",
-    "Denne API-en henter statistisk historisk data, herunder, statistisk data basert på de historiske dataene, ikke reele statistisk historisk. \n",
-    "\n",
-    "Statistikken er basert på de historiske datane total sett, ikke for hvert år."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "import os\n",
-    "\n",
-    "# Gets the absolute path to the src folder\n",
-    "sys.path.append(os.path.abspath(\"../src\"))\n",
-    "\n",
-    "# Now we can import the fucntion from the module\n",
-    "from my_package.year_data import fetch_data\n",
-    "\n",
-    "# User input the city, for the weather\n",
-    "city_name = input(\"Enter a city in Norway: \")\n",
-    "\n",
-    "data, folder = fetch_data(city_name)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Lagre data i json-fil\n",
-    "\n",
-    "Skriv inn navn for til filen du vil lagre med dataen.\n",
-    "\n",
-    "Eks. test\n",
-    "Da vil filen lagres som data_**test**.json, i mappen \"../data/output_statistikk/data_{filnavn}.json\"\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Gets the absolute path to the src folder\n",
-    "sys.path.append(os.path.abspath(\"../src\"))\n",
-    "\n",
-    "from my_package.write_data import write_data\n",
-    "\n",
-    "filename = input(\"Write filename: \")\n",
-    "\n",
-    "write_data(data, folder, filename)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Lese fra fil\n",
-    "\n",
-    "Henter opp data lagret i filen, lagd over, og skriver ut lesbart ved hjelp av pandas"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "\n",
-    "data = pd.read_json(f'../data/output_statistikk/data_{filename}.json')\n",
-    "\n",
-    "display(data)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "\n",
-    "if 'result' in data:\n",
-    "    df = pd.json_normalize(data['result'])\n",
-    "\n",
-    "    display(df)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Plotter data\n",
-    "Denne koden plotter data basert på gjennomsnitts temperatur gjennom året. For å sikre lagring av de ulike kjøringene, vil grafen bli lagret i mappen \"../data/output_fig/mean_temp_plot_{city_name}.json\"\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "import matplotlib.dates as mdates\n",
-    "import os\n",
-    "\n",
-    "output_folder = \"../data/output_fig\"\n",
-    "os.makedirs(output_folder, exist_ok=True)  # Create the folder if it doesn't exist\n",
-    "\n",
-    "# Converts to and make a new column with celsius temp, and not kelvin\n",
-    "df['temp.mean_celsius'] = df['temp.mean'] - 273.15\n",
-    "temp = df['temp.mean_celsius']\n",
-    "\n",
-    "# Convert from day and month, to datetime\n",
-    "# df['date'] = pd.to_datetime(df[['month', 'day']].assign(year=2024))\n",
-    "\n",
-    "# Create a new column that concatenates month and day (e.g., \"03-01\" for March 1)\n",
-    "df['month_day'] = df[['month', 'day']].apply(lambda x: f\"{x['month']:02d}-{x['day']:02d}\",axis=1)\n",
-    "\n",
-    "# Plot the graph of the mean temperature\n",
-    "plt.figure(figsize=(12, 6))\n",
-    "plt.plot(df['month_day'], temp)\n",
-    "\n",
-    "# Label for easier reading and understanding of the plot\n",
-    "plt.title(f\"Mean temp - statistic historical {city_name}\")\n",
-    "plt.xlabel(\"Date\")\n",
-    "plt.ylabel(\"Temperature (°C)\")\n",
-    "\n",
-    "# Customize the x-axis to show ticks and labels only at the start of each month\n",
-    "plt.gca().xaxis.set_major_locator(mdates.MonthLocator())  \n",
-    "# Format ticks to show abbreviated month names (e.g., Jan, Feb)\n",
-    "plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%b')) \n",
-    "\n",
-    "plt.xticks(rotation=45)\n",
-    "plt.yticks(range(-20, 30, 2))\n",
-    "plt.tight_layout()\n",
-    "plt.grid()\n",
-    "\n",
-    "# Save the plot to the data/output_fig folder\n",
-    "plot_path = os.path.join(output_folder, f\"mean_temp_plot_{city_name}.png\")\n",
-    "plt.savefig(plot_path)  # Save the plot as a PNG file\n",
-    "\n",
-    "# Show the plot\n",
-    "plt.show()\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "venv",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}