From f3e5046cf4e5d3ec15c726564c28bd87a1659e77 Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <kwanda2426@gmail.com>
Date: Sat, 30 Oct 2021 21:22:48 +0200
Subject: [PATCH 1/6] I just added new jypter nb

---
 starter-notebook.ipynb | 1025 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 1025 insertions(+)
 create mode 100644 starter-notebook.ipynb

diff --git a/starter-notebook.ipynb b/starter-notebook.ipynb
new file mode 100644
index 0000000..cdc1091
--- /dev/null
+++ b/starter-notebook.ipynb
@@ -0,0 +1,1025 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6c7e849a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2021-06-11T09:24:53.643384Z",
+     "start_time": "2021-06-11T09:24:53.622385Z"
+    }
+   },
+   "source": [
+    "# Regression Predict Student Solution\n",
+    "\n",
+    "© Explore Data Science Academy\n",
+    "\n",
+    "---\n",
+    "### Honour Code\n",
+    "\n",
+    "I {**YOUR NAME, YOUR SURNAME**}, confirm - by submitting this document - that the solutions in this notebook are a result of my own work and that I abide by the [EDSA honour code](https://drive.google.com/file/d/1QDCjGZJ8-FmJE3bZdIQNwnJyQKPhHZBn/view?usp=sharing).\n",
+    "\n",
+    "Non-compliance with the honour code constitutes a material breach of contract.\n",
+    "\n",
+    "### Predict Overview: Spain Electricity Shortfall Challenge\n",
+    "\n",
+    "The government of Spain is considering an expansion of it's renewable energy resource infrastructure investments. As such, they require information on the trends and patterns of the countries renewable sources and fossil fuel energy generation. Your company has been awarded the contract to:\n",
+    "\n",
+    "- 1. analyse the supplied data;\n",
+    "- 2. identify potential errors in the data and clean the existing data set;\n",
+    "- 3. determine if additional features can be added to enrich the data set;\n",
+    "- 4. build a model that is capable of forecasting the three hourly demand shortfalls;\n",
+    "- 5. evaluate the accuracy of the best machine learning model;\n",
+    "- 6. determine what features were most important in the model’s prediction decision, and\n",
+    "- 7. explain the inner working of the model to a non-technical audience.\n",
+    "\n",
+    "Formally the problem statement was given to you, the senior data scientist, by your manager via email reads as follow:\n",
+    "\n",
+    "> In this project you are tasked to model the shortfall between the energy generated by means of fossil fuels and various renewable sources - for the country of Spain. The daily shortfall, which will be referred to as the target variable, will be modelled as a function of various city-specific weather features such as `pressure`, `wind speed`, `humidity`, etc. As with all data science projects, the provided features are rarely adequate predictors of the target variable. As such, you are required to perform feature engineering to ensure that you will be able to accurately model Spain's three hourly shortfalls.\n",
+    " \n",
+    "On top of this, she has provided you with a starter notebook containing vague explanations of what the main outcomes are. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05600c92",
+   "metadata": {},
+   "source": [
+    "<a id=\"cont\"></a>\n",
+    "\n",
+    "## Table of Contents\n",
+    "\n",
+    "<a href=#one>1. Importing Packages</a>\n",
+    "\n",
+    "<a href=#two>2. Loading Data</a>\n",
+    "\n",
+    "<a href=#three>3. Exploratory Data Analysis (EDA)</a>\n",
+    "\n",
+    "<a href=#four>4. Data Engineering</a>\n",
+    "\n",
+    "<a href=#five>5. Modeling</a>\n",
+    "\n",
+    "<a href=#six>6. Model Performance</a>\n",
+    "\n",
+    "<a href=#seven>7. Model Explanations</a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "997462e2",
+   "metadata": {},
+   "source": [
+    " <a id=\"one\"></a>\n",
+    "## 1. Importing Packages\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Importing Packages ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section you are required to import, and briefly discuss, the libraries that will be used throughout your analysis and modelling. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "id": "475dbe93",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2021-06-23T10:30:53.800892Z",
+     "start_time": "2021-06-23T10:30:50.215449Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Libraries for data loading, data manipulation and data visulisation\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib import rc\n",
+    "import seaborn as sns\n",
+    "\n",
+    "#ignoring warnings\n",
+    "import warnings\n",
+    "warnings.simplefilter(action='ignore')\n",
+    "\n",
+    "\n",
+    "# Libraries for data preparation and model building\n",
+    "from sklearn import metrics\n",
+    "from sklearn.tree import DecisionTreeRegressor\n",
+    "from sklearn.compose import ColumnTransformer\n",
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.linear_model import Lasso, Ridge, LinearRegression\n",
+    "from sklearn.model_selection import train_test_split, KFold, cross_val_score, GridSearchCV\n",
+    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler, PolynomialFeatures\n",
+    "# saving my model\n",
+    "import pickle\n",
+    "\n",
+    "# Setting global constants to ensure notebook results are reproducible\n",
+    "#PARAMETER_CONSTANT = ###"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f22a6718",
+   "metadata": {},
+   "source": [
+    "<a id=\"two\"></a>\n",
+    "## 2. Loading the Data\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Loading the data ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section you are required to load the data from the `df_train` file into a DataFrame. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "id": "2b0a9c54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#making sure that we can see all rows and cols\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "pd.set_option('display.max_rows', None)\n",
+    "#reading the data from the csv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 91,
+   "id": "fbbb6c18",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2021-06-28T08:49:35.311495Z",
+     "start_time": "2021-06-28T08:49:35.295494Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "##########################################################################################################\n",
+    "df = pd.read_csv('df_train.csv')\n",
+    "test_df = pd.read_csv('df_test.csv')\n",
+    "\n",
+    "df_1 = df.copy()\n",
+    "\n",
+    "df_1['time'] = pd.to_datetime(df_1['time']) # changing the date datatype\n",
+    "\n",
+    "#cols_to_drop = [item for item in df.columns if 'weather' in item or '_deg' in item]\n",
+    "\n",
+    "df_1.drop('Unnamed: 0',inplace = True,axis = 1) #deleting the first column\n",
+    "\n",
+    "#df_1.drop(cols_to_drop,inplace = True,axis = 1)\n",
+    "\n",
+    "df_1.drop_duplicates(keep=False,inplace=True) #removing duplicates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 92,
+   "id": "773d448b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mean_ = df_1['Valencia_pressure'].mean()\n",
+    "\n",
+    "df_1['Valencia_pressure'] = df_1['Valencia_pressure'].fillna(mean_)\n",
+    "\n",
+    "df_cols = df_1.columns\n",
+    "\n",
+    "cat_cols = [item for item in df_cols if 'pressure' in item]\n",
+    "\n",
+    "df_1[cat_cols] = df_1[cat_cols].astype('category')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "id": "7c359246",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(8763, 48)"
+      ]
+     },
+     "execution_count": 93,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_1.shape\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "id": "d12bf270",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols = [item for item in df_1.columns if 'deg' in item or 'sure' in item]\n",
+    "col = [item + \"_\" for item in df_1.columns if 'deg' in item or 'sure' in item]\n",
+    "\n",
+    "for item in range(0,len(cols)):\n",
+    "    from sklearn.preprocessing import LabelEncoder\n",
+    "    le = LabelEncoder()\n",
+    "    \n",
+    "    df_1[col[item]] = le.fit_transform(df_1[cols[item]])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "36286386",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_1.drop(cols,inplace = True,axis = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "id": "3c8f0f53",
+   "metadata": {},
+   "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>time</th>\n",
+       "      <th>Madrid_wind_speed</th>\n",
+       "      <th>Bilbao_rain_1h</th>\n",
+       "      <th>Valencia_wind_speed</th>\n",
+       "      <th>Seville_humidity</th>\n",
+       "      <th>Madrid_humidity</th>\n",
+       "      <th>Bilbao_clouds_all</th>\n",
+       "      <th>Bilbao_wind_speed</th>\n",
+       "      <th>Seville_clouds_all</th>\n",
+       "      <th>Barcelona_wind_speed</th>\n",
+       "      <th>Madrid_clouds_all</th>\n",
+       "      <th>Seville_wind_speed</th>\n",
+       "      <th>Barcelona_rain_1h</th>\n",
+       "      <th>Seville_rain_1h</th>\n",
+       "      <th>Bilbao_snow_3h</th>\n",
+       "      <th>Seville_rain_3h</th>\n",
+       "      <th>Madrid_rain_1h</th>\n",
+       "      <th>Barcelona_rain_3h</th>\n",
+       "      <th>Valencia_snow_3h</th>\n",
+       "      <th>Madrid_weather_id</th>\n",
+       "      <th>Barcelona_weather_id</th>\n",
+       "      <th>Seville_weather_id</th>\n",
+       "      <th>Seville_temp_max</th>\n",
+       "      <th>Valencia_temp_max</th>\n",
+       "      <th>Valencia_temp</th>\n",
+       "      <th>Bilbao_weather_id</th>\n",
+       "      <th>Seville_temp</th>\n",
+       "      <th>Valencia_humidity</th>\n",
+       "      <th>Valencia_temp_min</th>\n",
+       "      <th>Barcelona_temp_max</th>\n",
+       "      <th>Madrid_temp_max</th>\n",
+       "      <th>Barcelona_temp</th>\n",
+       "      <th>Bilbao_temp_min</th>\n",
+       "      <th>Bilbao_temp</th>\n",
+       "      <th>Barcelona_temp_min</th>\n",
+       "      <th>Bilbao_temp_max</th>\n",
+       "      <th>Seville_temp_min</th>\n",
+       "      <th>Madrid_temp</th>\n",
+       "      <th>Madrid_temp_min</th>\n",
+       "      <th>load_shortfall_3h</th>\n",
+       "      <th>Valencia_wind_deg_</th>\n",
+       "      <th>Bilbao_wind_deg_</th>\n",
+       "      <th>Barcelona_wind_deg_</th>\n",
+       "      <th>Seville_pressure_</th>\n",
+       "      <th>Barcelona_pressure_</th>\n",
+       "      <th>Bilbao_pressure_</th>\n",
+       "      <th>Valencia_pressure_</th>\n",
+       "      <th>Madrid_pressure_</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2015-01-01 03:00:00</td>\n",
+       "      <td>0.666667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.666667</td>\n",
+       "      <td>74.333333</td>\n",
+       "      <td>64.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>274.254667</td>\n",
+       "      <td>269.888000</td>\n",
+       "      <td>269.888000</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>274.254667</td>\n",
+       "      <td>75.666667</td>\n",
+       "      <td>269.888000</td>\n",
+       "      <td>281.013000</td>\n",
+       "      <td>265.938000</td>\n",
+       "      <td>281.013000</td>\n",
+       "      <td>269.338615</td>\n",
+       "      <td>269.338615</td>\n",
+       "      <td>281.013000</td>\n",
+       "      <td>269.338615</td>\n",
+       "      <td>274.254667</td>\n",
+       "      <td>265.938000</td>\n",
+       "      <td>265.938000</td>\n",
+       "      <td>6715.666667</td>\n",
+       "      <td>5</td>\n",
+       "      <td>663</td>\n",
+       "      <td>97</td>\n",
+       "      <td>17</td>\n",
+       "      <td>163</td>\n",
+       "      <td>184</td>\n",
+       "      <td>84</td>\n",
+       "      <td>115</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2015-01-01 06:00:00</td>\n",
+       "      <td>0.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.666667</td>\n",
+       "      <td>78.333333</td>\n",
+       "      <td>64.666667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>274.945000</td>\n",
+       "      <td>271.728333</td>\n",
+       "      <td>271.728333</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>274.945000</td>\n",
+       "      <td>71.000000</td>\n",
+       "      <td>271.728333</td>\n",
+       "      <td>280.561667</td>\n",
+       "      <td>266.386667</td>\n",
+       "      <td>280.561667</td>\n",
+       "      <td>270.376000</td>\n",
+       "      <td>270.376000</td>\n",
+       "      <td>280.561667</td>\n",
+       "      <td>270.376000</td>\n",
+       "      <td>274.945000</td>\n",
+       "      <td>266.386667</td>\n",
+       "      <td>266.386667</td>\n",
+       "      <td>4171.666667</td>\n",
+       "      <td>1</td>\n",
+       "      <td>656</td>\n",
+       "      <td>374</td>\n",
+       "      <td>17</td>\n",
+       "      <td>166</td>\n",
+       "      <td>186</td>\n",
+       "      <td>89</td>\n",
+       "      <td>119</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2015-01-01 09:00:00</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>71.333333</td>\n",
+       "      <td>64.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.666667</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>278.792000</td>\n",
+       "      <td>278.008667</td>\n",
+       "      <td>278.008667</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>278.792000</td>\n",
+       "      <td>65.666667</td>\n",
+       "      <td>278.008667</td>\n",
+       "      <td>281.583667</td>\n",
+       "      <td>272.708667</td>\n",
+       "      <td>281.583667</td>\n",
+       "      <td>275.027229</td>\n",
+       "      <td>275.027229</td>\n",
+       "      <td>281.583667</td>\n",
+       "      <td>275.027229</td>\n",
+       "      <td>278.792000</td>\n",
+       "      <td>272.708667</td>\n",
+       "      <td>272.708667</td>\n",
+       "      <td>4274.666667</td>\n",
+       "      <td>9</td>\n",
+       "      <td>636</td>\n",
+       "      <td>923</td>\n",
+       "      <td>17</td>\n",
+       "      <td>168</td>\n",
+       "      <td>187</td>\n",
+       "      <td>92</td>\n",
+       "      <td>123</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2015-01-01 12:00:00</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>65.333333</td>\n",
+       "      <td>56.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>285.394000</td>\n",
+       "      <td>284.899552</td>\n",
+       "      <td>284.899552</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>285.394000</td>\n",
+       "      <td>54.000000</td>\n",
+       "      <td>284.899552</td>\n",
+       "      <td>283.434104</td>\n",
+       "      <td>281.895219</td>\n",
+       "      <td>283.434104</td>\n",
+       "      <td>281.135063</td>\n",
+       "      <td>281.135063</td>\n",
+       "      <td>283.434104</td>\n",
+       "      <td>281.135063</td>\n",
+       "      <td>285.394000</td>\n",
+       "      <td>281.895219</td>\n",
+       "      <td>281.895219</td>\n",
+       "      <td>5075.666667</td>\n",
+       "      <td>8</td>\n",
+       "      <td>592</td>\n",
+       "      <td>770</td>\n",
+       "      <td>17</td>\n",
+       "      <td>165</td>\n",
+       "      <td>187</td>\n",
+       "      <td>103</td>\n",
+       "      <td>168</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2015-01-01 15:00:00</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>59.000000</td>\n",
+       "      <td>57.000000</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.333333</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.000000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>285.513719</td>\n",
+       "      <td>283.015115</td>\n",
+       "      <td>283.015115</td>\n",
+       "      <td>800.0</td>\n",
+       "      <td>285.513719</td>\n",
+       "      <td>58.333333</td>\n",
+       "      <td>283.015115</td>\n",
+       "      <td>284.213167</td>\n",
+       "      <td>280.678437</td>\n",
+       "      <td>284.213167</td>\n",
+       "      <td>282.252063</td>\n",
+       "      <td>282.252063</td>\n",
+       "      <td>284.213167</td>\n",
+       "      <td>282.252063</td>\n",
+       "      <td>285.513719</td>\n",
+       "      <td>280.678437</td>\n",
+       "      <td>280.678437</td>\n",
+       "      <td>6620.666667</td>\n",
+       "      <td>7</td>\n",
+       "      <td>548</td>\n",
+       "      <td>731</td>\n",
+       "      <td>17</td>\n",
+       "      <td>159</td>\n",
+       "      <td>185</td>\n",
+       "      <td>113</td>\n",
+       "      <td>289</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 time  Madrid_wind_speed  Bilbao_rain_1h  Valencia_wind_speed  \\\n",
+       "0 2015-01-01 03:00:00           0.666667             0.0             0.666667   \n",
+       "1 2015-01-01 06:00:00           0.333333             0.0             1.666667   \n",
+       "2 2015-01-01 09:00:00           1.000000             0.0             1.000000   \n",
+       "3 2015-01-01 12:00:00           1.000000             0.0             1.000000   \n",
+       "4 2015-01-01 15:00:00           1.000000             0.0             1.000000   \n",
+       "\n",
+       "   Seville_humidity  Madrid_humidity  Bilbao_clouds_all  Bilbao_wind_speed  \\\n",
+       "0         74.333333        64.000000                0.0           1.000000   \n",
+       "1         78.333333        64.666667                0.0           1.000000   \n",
+       "2         71.333333        64.333333                0.0           1.000000   \n",
+       "3         65.333333        56.333333                0.0           1.000000   \n",
+       "4         59.000000        57.000000                2.0           0.333333   \n",
+       "\n",
+       "   Seville_clouds_all  Barcelona_wind_speed  Madrid_clouds_all  \\\n",
+       "0                 0.0              6.333333                0.0   \n",
+       "1                 0.0              4.000000                0.0   \n",
+       "2                 0.0              2.000000                0.0   \n",
+       "3                 0.0              2.333333                0.0   \n",
+       "4                 0.0              4.333333                0.0   \n",
+       "\n",
+       "   Seville_wind_speed  Barcelona_rain_1h  Seville_rain_1h  Bilbao_snow_3h  \\\n",
+       "0            3.333333                0.0              0.0             0.0   \n",
+       "1            3.333333                0.0              0.0             0.0   \n",
+       "2            2.666667                0.0              0.0             0.0   \n",
+       "3            4.000000                0.0              0.0             0.0   \n",
+       "4            3.000000                0.0              0.0             0.0   \n",
+       "\n",
+       "   Seville_rain_3h  Madrid_rain_1h  Barcelona_rain_3h  Valencia_snow_3h  \\\n",
+       "0              0.0             0.0                0.0               0.0   \n",
+       "1              0.0             0.0                0.0               0.0   \n",
+       "2              0.0             0.0                0.0               0.0   \n",
+       "3              0.0             0.0                0.0               0.0   \n",
+       "4              0.0             0.0                0.0               0.0   \n",
+       "\n",
+       "   Madrid_weather_id  Barcelona_weather_id  Seville_weather_id  \\\n",
+       "0              800.0                 800.0               800.0   \n",
+       "1              800.0                 800.0               800.0   \n",
+       "2              800.0                 800.0               800.0   \n",
+       "3              800.0                 800.0               800.0   \n",
+       "4              800.0                 800.0               800.0   \n",
+       "\n",
+       "   Seville_temp_max  Valencia_temp_max  Valencia_temp  Bilbao_weather_id  \\\n",
+       "0        274.254667         269.888000     269.888000              800.0   \n",
+       "1        274.945000         271.728333     271.728333              800.0   \n",
+       "2        278.792000         278.008667     278.008667              800.0   \n",
+       "3        285.394000         284.899552     284.899552              800.0   \n",
+       "4        285.513719         283.015115     283.015115              800.0   \n",
+       "\n",
+       "   Seville_temp  Valencia_humidity  Valencia_temp_min  Barcelona_temp_max  \\\n",
+       "0    274.254667          75.666667         269.888000          281.013000   \n",
+       "1    274.945000          71.000000         271.728333          280.561667   \n",
+       "2    278.792000          65.666667         278.008667          281.583667   \n",
+       "3    285.394000          54.000000         284.899552          283.434104   \n",
+       "4    285.513719          58.333333         283.015115          284.213167   \n",
+       "\n",
+       "   Madrid_temp_max  Barcelona_temp  Bilbao_temp_min  Bilbao_temp  \\\n",
+       "0       265.938000      281.013000       269.338615   269.338615   \n",
+       "1       266.386667      280.561667       270.376000   270.376000   \n",
+       "2       272.708667      281.583667       275.027229   275.027229   \n",
+       "3       281.895219      283.434104       281.135063   281.135063   \n",
+       "4       280.678437      284.213167       282.252063   282.252063   \n",
+       "\n",
+       "   Barcelona_temp_min  Bilbao_temp_max  Seville_temp_min  Madrid_temp  \\\n",
+       "0          281.013000       269.338615        274.254667   265.938000   \n",
+       "1          280.561667       270.376000        274.945000   266.386667   \n",
+       "2          281.583667       275.027229        278.792000   272.708667   \n",
+       "3          283.434104       281.135063        285.394000   281.895219   \n",
+       "4          284.213167       282.252063        285.513719   280.678437   \n",
+       "\n",
+       "   Madrid_temp_min  load_shortfall_3h  Valencia_wind_deg_  Bilbao_wind_deg_  \\\n",
+       "0       265.938000        6715.666667                   5               663   \n",
+       "1       266.386667        4171.666667                   1               656   \n",
+       "2       272.708667        4274.666667                   9               636   \n",
+       "3       281.895219        5075.666667                   8               592   \n",
+       "4       280.678437        6620.666667                   7               548   \n",
+       "\n",
+       "   Barcelona_wind_deg_  Seville_pressure_  Barcelona_pressure_  \\\n",
+       "0                   97                 17                  163   \n",
+       "1                  374                 17                  166   \n",
+       "2                  923                 17                  168   \n",
+       "3                  770                 17                  165   \n",
+       "4                  731                 17                  159   \n",
+       "\n",
+       "   Bilbao_pressure_  Valencia_pressure_  Madrid_pressure_  \n",
+       "0               184                  84               115  \n",
+       "1               186                  89               119  \n",
+       "2               187                  92               123  \n",
+       "3               187                 103               168  \n",
+       "4               185                 113               289  "
+      ]
+     },
+     "execution_count": 96,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_1.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81132ab3",
+   "metadata": {},
+   "source": [
+    "<a id=\"three\"></a>\n",
+    "## 3. Exploratory Data Analysis (EDA)\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Exploratory data analysis ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section, you are required to perform an in-depth analysis of all the variables in the DataFrame. |\n",
+    "\n",
+    "---\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "e805134e",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2021-06-28T08:52:37.824204Z",
+     "start_time": "2021-06-28T08:52:37.811206Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(8763, 892)"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# look at data statistics\n",
+    "df_1.corr()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2fb74182",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# plot relevant feature interactions\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6dd6ee8c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# evaluate correlation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de51df85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# have a look at feature distributions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3fa93ec6",
+   "metadata": {},
+   "source": [
+    "<a id=\"four\"></a>\n",
+    "## 4. Data Engineering\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Data engineering ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section you are required to: clean the dataset, and possibly create new features - as identified in the EDA phase. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "059c2f3e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# remove missing values/ features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "84eea17b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create new features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "59692724",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# engineer existing features"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43b2d523",
+   "metadata": {},
+   "source": [
+    "<a id=\"five\"></a>\n",
+    "## 5. Modelling\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Modelling ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section, you are required to create one or more regression models that are able to accurately predict the thee hour load shortfall. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2344b3e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# split data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c58df02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create targets and features dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20d073e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create one or more ML models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a70c15d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# evaluate one or more ML models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b530251",
+   "metadata": {},
+   "source": [
+    "<a id=\"six\"></a>\n",
+    "## 6. Model Performance\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Model performance ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section you are required to compare the relative performance of the various trained ML models on a holdout dataset and comment on what model is the best and why. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a69b5a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Compare model performance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3874a7c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Choose best model and motivate why it is the best choice"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a8ad0c0d",
+   "metadata": {},
+   "source": [
+    "<a id=\"seven\"></a>\n",
+    "## 7. Model Explanations\n",
+    "<a class=\"anchor\" id=\"1.1\"></a>\n",
+    "<a href=#cont>Back to Table of Contents</a>\n",
+    "\n",
+    "---\n",
+    "    \n",
+    "| ⚡ Description: Model explanation ⚡ |\n",
+    "| :--------------------------- |\n",
+    "| In this section, you are required to discuss how the best performing model works in a simple way so that both technical and non-technical stakeholders can grasp the intuition behind the model's inner workings. |\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5ff741c2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# discuss chosen methods logic"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.8"
+  },
+  "latex_envs": {
+   "LaTeX_envs_menu_present": true,
+   "autoclose": false,
+   "autocomplete": true,
+   "bibliofile": "biblio.bib",
+   "cite_by": "apalike",
+   "current_citInitial": 1,
+   "eqLabelWithNumbers": true,
+   "eqNumInitial": 1,
+   "hotkeys": {
+    "equation": "Ctrl-E",
+    "itemize": "Ctrl-I"
+   },
+   "labels_anchors": false,
+   "latex_user_defs": false,
+   "report_style_numbering": false,
+   "user_envs_cfg": false
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From d7068ba61dd65c66ed77ace70cfd31e34a88c0c4 Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <90265907+kwanda2426@users.noreply.github.com>
Date: Thu, 4 Nov 2021 16:03:00 +0200
Subject: [PATCH 2/6] I have created a model

This contains a working
---
 adding temp.ipynb | 2229 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 2229 insertions(+)
 create mode 100644 adding temp.ipynb

diff --git a/adding temp.ipynb b/adding temp.ipynb
new file mode 100644
index 0000000..786ee0e
--- /dev/null
+++ b/adding temp.ipynb	
@@ -0,0 +1,2229 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "656660f4",
+   "metadata": {},
+   "source": [
+    "# Regression Predict Student Solution\n",
+    "\n",
+    "© Explore Data Science Academy\n",
+    "\n",
+    "---\n",
+    "### Honour Code\n",
+    "\n",
+    "I {**YOUR NAME, YOUR SURNAME**}, confirm - by submitting this document - that the solutions in this notebook are a result of my own work and that I abide by the [EDSA honour code](https://drive.google.com/file/d/1QDCjGZJ8-FmJE3bZdIQNwnJyQKPhHZBn/view?usp=sharing).\n",
+    "\n",
+    "Non-compliance with the honour code constitutes a material breach of contract."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "11cae5b0",
+   "metadata": {},
+   "source": [
+    "# 1. Importing Packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "id": "5f1edcab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Libraries for data loading, data manipulation and data visulisation\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib import rc\n",
+    "import seaborn as sns\n",
+    "from statsmodels.graphics.correlation import plot_corr\n",
+    "from scipy.stats import skew\n",
+    "#ignoring warnings\n",
+    "import warnings\n",
+    "warnings.simplefilter(action='ignore')\n",
+    "import datetime\n",
+    "\n",
+    "# Libraries for data preparation and model building\n",
+    "import statsmodels.formula.api as sm\n",
+    "from sklearn import metrics\n",
+    "from sklearn.metrics import mean_squared_error\n",
+    "from sklearn.tree import DecisionTreeRegressor\n",
+    "from sklearn.compose import ColumnTransformer\n",
+    "from sklearn.ensemble import RandomForestRegressor\n",
+    "from sklearn.linear_model import Lasso, Ridge, LinearRegression\n",
+    "from sklearn.model_selection import train_test_split, KFold, cross_val_score, GridSearchCV\n",
+    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler, PolynomialFeatures\n",
+    "# saving my model\n",
+    "import pickle\n",
+    "\n",
+    "# Setting global constants to ensure notebook results are reproducible\n",
+    "PARAMETER_CONSTANT = 0.01"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6c6c86fe",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91282391",
+   "metadata": {},
+   "source": [
+    "# 2. Loading the Data\n",
+    " "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "633bd2ba",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "id": "d3e62dd0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#making sure that we can see all rows and cols\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "pd.set_option('display.max_rows', None)\n",
+    "#reading the data from the csv\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "id": "9df7c655",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "df = pd.read_csv('df_train.csv')\n",
+    "test_df = pd.read_csv('df_test.csv')\n",
+    "df_test = test_df.copy()\n",
+    "df_1 = df.copy()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ee5dd71",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3be62cd",
+   "metadata": {},
+   "source": [
+    "# 3. Exploratory Data Analysis (EDA)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4023d99",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "id": "24459be3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(8763, 49)"
+      ]
+     },
+     "execution_count": 106,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#From the shape it is observed that the DataFrame has 8763 rows and 49 columns\n",
+    "\n",
+    "df_1.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b16a012",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d411743c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3389ab4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "id": "fefaef12",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 8763 entries, 0 to 8762\n",
+      "Data columns (total 49 columns):\n",
+      " #   Column                Non-Null Count  Dtype  \n",
+      "---  ------                --------------  -----  \n",
+      " 0   Unnamed: 0            8763 non-null   int64  \n",
+      " 1   time                  8763 non-null   object \n",
+      " 2   Madrid_wind_speed     8763 non-null   float64\n",
+      " 3   Valencia_wind_deg     8763 non-null   object \n",
+      " 4   Bilbao_rain_1h        8763 non-null   float64\n",
+      " 5   Valencia_wind_speed   8763 non-null   float64\n",
+      " 6   Seville_humidity      8763 non-null   float64\n",
+      " 7   Madrid_humidity       8763 non-null   float64\n",
+      " 8   Bilbao_clouds_all     8763 non-null   float64\n",
+      " 9   Bilbao_wind_speed     8763 non-null   float64\n",
+      " 10  Seville_clouds_all    8763 non-null   float64\n",
+      " 11  Bilbao_wind_deg       8763 non-null   float64\n",
+      " 12  Barcelona_wind_speed  8763 non-null   float64\n",
+      " 13  Barcelona_wind_deg    8763 non-null   float64\n",
+      " 14  Madrid_clouds_all     8763 non-null   float64\n",
+      " 15  Seville_wind_speed    8763 non-null   float64\n",
+      " 16  Barcelona_rain_1h     8763 non-null   float64\n",
+      " 17  Seville_pressure      8763 non-null   object \n",
+      " 18  Seville_rain_1h       8763 non-null   float64\n",
+      " 19  Bilbao_snow_3h        8763 non-null   float64\n",
+      " 20  Barcelona_pressure    8763 non-null   float64\n",
+      " 21  Seville_rain_3h       8763 non-null   float64\n",
+      " 22  Madrid_rain_1h        8763 non-null   float64\n",
+      " 23  Barcelona_rain_3h     8763 non-null   float64\n",
+      " 24  Valencia_snow_3h      8763 non-null   float64\n",
+      " 25  Madrid_weather_id     8763 non-null   float64\n",
+      " 26  Barcelona_weather_id  8763 non-null   float64\n",
+      " 27  Bilbao_pressure       8763 non-null   float64\n",
+      " 28  Seville_weather_id    8763 non-null   float64\n",
+      " 29  Valencia_pressure     6695 non-null   float64\n",
+      " 30  Seville_temp_max      8763 non-null   float64\n",
+      " 31  Madrid_pressure       8763 non-null   float64\n",
+      " 32  Valencia_temp_max     8763 non-null   float64\n",
+      " 33  Valencia_temp         8763 non-null   float64\n",
+      " 34  Bilbao_weather_id     8763 non-null   float64\n",
+      " 35  Seville_temp          8763 non-null   float64\n",
+      " 36  Valencia_humidity     8763 non-null   float64\n",
+      " 37  Valencia_temp_min     8763 non-null   float64\n",
+      " 38  Barcelona_temp_max    8763 non-null   float64\n",
+      " 39  Madrid_temp_max       8763 non-null   float64\n",
+      " 40  Barcelona_temp        8763 non-null   float64\n",
+      " 41  Bilbao_temp_min       8763 non-null   float64\n",
+      " 42  Bilbao_temp           8763 non-null   float64\n",
+      " 43  Barcelona_temp_min    8763 non-null   float64\n",
+      " 44  Bilbao_temp_max       8763 non-null   float64\n",
+      " 45  Seville_temp_min      8763 non-null   float64\n",
+      " 46  Madrid_temp           8763 non-null   float64\n",
+      " 47  Madrid_temp_min       8763 non-null   float64\n",
+      " 48  load_shortfall_3h     8763 non-null   float64\n",
+      "dtypes: float64(45), int64(1), object(3)\n",
+      "memory usage: 3.3+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "#The DataFrame has 1 column that has Null values \n",
+    "#3 columns with 'object' data type \n",
+    "\n",
+    "df_1.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "id": "74771c6f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Filing in the NAN with mean() as it was observed above that Valencia_pressure has null values\n",
+    "\n",
+    "df_1['Valencia_pressure'].fillna(df_1['Valencia_pressure'].mean(), inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "486ca065",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "id": "96952d7a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_1['time'] = pd.to_datetime(df_1['time']) # changing the date datatype\n",
+    "\n",
+    "test_df['time'] = pd.to_datetime(test_df['time']) # changing the date datatype\n",
+    "#cols_to_drop = [item for item in df.columns if 'weather' in item or '_deg' in item]\n",
+    "\n",
+    "df_test.drop('Unnamed: 0',inplace = True,axis = 1) #deleting the first column\n",
+    "\n",
+    "df_1.drop('Unnamed: 0',inplace = True,axis = 1) #deleting the first column"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "id": "02e4e5d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cols_to_drop = ['Bilbao_rain_1h','Bilbao_wind_deg','Barcelona_pressure','Barcelona_wind_deg',\n",
+    "               'Barcelona_rain_1h','Seville_rain_1h','Bilbao_pressure','Madrid_pressure','Valencia_pressure']\n",
+    "\n",
+    "cols = [item for item in df_1.columns if 'max' in item or 'min' in item or '1h' in item]\n",
+    "\n",
+    "cols_to = cols_to_drop + cols\n",
+    "\n",
+    "df_1.drop(cols_to, inplace = True, axis = 1)\n",
+    "\n",
+    "test_df.drop(cols_to, inplace = True, axis = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "id": "1b064efe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "#Changing Dtypes of 'time' from object to 'datetime64'\n",
+    "#Changing Dtypes of 'Valencia_wind_deg', 'Seville_pressure' from object to 'category'\n",
+    "\n",
+    "\n",
+    "cat_cols = [item for item in df_1.columns if 'pressure' in item or 'deg' in item]\n",
+    "\n",
+    "test_cols = [item for item in test_df.columns if 'pressure' in item or 'deg' in item]\n",
+    "\n",
+    "df_1[cat_cols] = df_1[cat_cols].astype('category')\n",
+    "\n",
+    "test_df[test_cols] = test_df[test_cols].astype('category')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2245b60d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "id": "7f05732c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Encoding 'Valencia_wind_deg', 'Seville_pressure' from 'category' to numeric values using 'cat.codes'\n",
+    "\n",
+    "\n",
+    "df_1['Valencia_wind_deg'] = df_1['Valencia_wind_deg'].cat.codes\n",
+    "\n",
+    "\n",
+    "df_1['Seville_pressure'] = df_1['Seville_pressure'].cat.codes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "id": "ef967837",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Encoding 'Valencia_wind_deg', 'Seville_pressure' from 'category' to numeric values using 'cat.codes'\n",
+    "\n",
+    "\n",
+    "test_df['Valencia_wind_deg'] = test_df['Valencia_wind_deg'].cat.codes\n",
+    "\n",
+    "\n",
+    "test_df['Seville_pressure'] = test_df['Seville_pressure'].cat.codes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55821e0d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "id": "71dae5ea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#extracing the date from date time\n",
+    "\n",
+    "df_1['month'] = df_1['time'].dt.month\n",
+    "df_1['day'] = df_1['time'].dt.day\n",
+    "df_1['time'] = df_1['time'].dt.time\n",
+    "\n",
+    "test_df['month'] = test_df['time'].dt.month\n",
+    "test_df['day'] = test_df['time'].dt.day\n",
+    "test_df['time'] = test_df['time'].dt.time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "id": "4bbbbce5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1440x1440 with 20 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "features  = ['Madrid_temp', \"Bilbao_temp\", 'Barcelona_temp', \"Valencia_temp\", \"Valencia_humidity\",\"Seville_temp\", \"Valencia_snow_3h\", \"Seville_rain_3h\", \"Barcelona_rain_3h\", \"Bilbao_snow_3h\", \"Madrid_clouds_all\", \"Bilbao_clouds_all\", \"Madrid_humidity\", \"Seville_humidity\", \"Valencia_wind_speed\", \"Madrid_wind_speed\", \"Valencia_wind_deg\", \"Bilbao_snow_3h\"]\n",
+    "df_1[features].hist(figsize=(20,20));"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "47d49539",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "id": "dc462929",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1440x1440 with 25 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df[features].plot(kind='density', subplots=True, layout=(5, 5), sharex=False, figsize=(20, 20));"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "89d65752",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "id": "7f533883",
+   "metadata": {},
+   "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>Madrid_wind_speed</th>\n",
+       "      <th>Valencia_wind_deg</th>\n",
+       "      <th>Valencia_wind_speed</th>\n",
+       "      <th>Seville_humidity</th>\n",
+       "      <th>Madrid_humidity</th>\n",
+       "      <th>Bilbao_clouds_all</th>\n",
+       "      <th>Bilbao_wind_speed</th>\n",
+       "      <th>Seville_clouds_all</th>\n",
+       "      <th>Barcelona_wind_speed</th>\n",
+       "      <th>Madrid_clouds_all</th>\n",
+       "      <th>Seville_wind_speed</th>\n",
+       "      <th>Seville_pressure</th>\n",
+       "      <th>Bilbao_snow_3h</th>\n",
+       "      <th>Seville_rain_3h</th>\n",
+       "      <th>Barcelona_rain_3h</th>\n",
+       "      <th>Valencia_snow_3h</th>\n",
+       "      <th>Madrid_weather_id</th>\n",
+       "      <th>Barcelona_weather_id</th>\n",
+       "      <th>Seville_weather_id</th>\n",
+       "      <th>Valencia_temp</th>\n",
+       "      <th>Bilbao_weather_id</th>\n",
+       "      <th>Seville_temp</th>\n",
+       "      <th>Valencia_humidity</th>\n",
+       "      <th>Barcelona_temp</th>\n",
+       "      <th>Bilbao_temp</th>\n",
+       "      <th>Madrid_temp</th>\n",
+       "      <th>load_shortfall_3h</th>\n",
+       "      <th>month</th>\n",
+       "      <th>day</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Madrid_wind_speed</th>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.104954</td>\n",
+       "      <td>0.513092</td>\n",
+       "      <td>-0.117892</td>\n",
+       "      <td>-0.137092</td>\n",
+       "      <td>0.244001</td>\n",
+       "      <td>0.377854</td>\n",
+       "      <td>0.191251</td>\n",
+       "      <td>0.294640</td>\n",
+       "      <td>0.230126</td>\n",
+       "      <td>0.434104</td>\n",
+       "      <td>-0.026246</td>\n",
+       "      <td>0.071183</td>\n",
+       "      <td>0.004795</td>\n",
+       "      <td>-0.014644</td>\n",
+       "      <td>0.021660</td>\n",
+       "      <td>-0.169358</td>\n",
+       "      <td>-0.099582</td>\n",
+       "      <td>-0.120014</td>\n",
+       "      <td>0.128726</td>\n",
+       "      <td>-0.238128</td>\n",
+       "      <td>0.090861</td>\n",
+       "      <td>-0.285787</td>\n",
+       "      <td>0.080133</td>\n",
+       "      <td>0.060467</td>\n",
+       "      <td>0.109572</td>\n",
+       "      <td>-0.150981</td>\n",
+       "      <td>-0.237445</td>\n",
+       "      <td>-0.029954</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Valencia_wind_deg</th>\n",
+       "      <td>0.104954</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.204874</td>\n",
+       "      <td>0.141594</td>\n",
+       "      <td>0.171478</td>\n",
+       "      <td>0.074476</td>\n",
+       "      <td>0.112475</td>\n",
+       "      <td>0.109314</td>\n",
+       "      <td>0.116735</td>\n",
+       "      <td>0.129917</td>\n",
+       "      <td>0.007634</td>\n",
+       "      <td>-0.043797</td>\n",
+       "      <td>-0.005715</td>\n",
+       "      <td>-0.007180</td>\n",
+       "      <td>0.015736</td>\n",
+       "      <td>-0.003976</td>\n",
+       "      <td>-0.027027</td>\n",
+       "      <td>-0.000043</td>\n",
+       "      <td>-0.020651</td>\n",
+       "      <td>-0.084541</td>\n",
+       "      <td>-0.099664</td>\n",
+       "      <td>-0.151280</td>\n",
+       "      <td>-0.198984</td>\n",
+       "      <td>-0.113788</td>\n",
+       "      <td>-0.099050</td>\n",
+       "      <td>-0.166092</td>\n",
+       "      <td>-0.110849</td>\n",
+       "      <td>-0.087571</td>\n",
+       "      <td>-0.025467</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Valencia_wind_speed</th>\n",
+       "      <td>0.513092</td>\n",
+       "      <td>0.204874</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.075227</td>\n",
+       "      <td>-0.019388</td>\n",
+       "      <td>0.210524</td>\n",
+       "      <td>0.386478</td>\n",
+       "      <td>0.163675</td>\n",
+       "      <td>0.347966</td>\n",
+       "      <td>0.221887</td>\n",
+       "      <td>0.316035</td>\n",
+       "      <td>-0.010144</td>\n",
+       "      <td>0.115133</td>\n",
+       "      <td>0.027637</td>\n",
+       "      <td>-0.037553</td>\n",
+       "      <td>0.058629</td>\n",
+       "      <td>-0.099056</td>\n",
+       "      <td>-0.037605</td>\n",
+       "      <td>-0.069092</td>\n",
+       "      <td>0.072366</td>\n",
+       "      <td>-0.201379</td>\n",
+       "      <td>-0.008508</td>\n",
+       "      <td>-0.413017</td>\n",
+       "      <td>-0.021456</td>\n",
+       "      <td>-0.022676</td>\n",
+       "      <td>-0.011982</td>\n",
+       "      <td>-0.142791</td>\n",
+       "      <td>-0.237156</td>\n",
+       "      <td>-0.000340</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_humidity</th>\n",
+       "      <td>-0.117892</td>\n",
+       "      <td>0.141594</td>\n",
+       "      <td>-0.075227</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.799831</td>\n",
+       "      <td>0.061680</td>\n",
+       "      <td>-0.088180</td>\n",
+       "      <td>0.399436</td>\n",
+       "      <td>-0.138625</td>\n",
+       "      <td>0.366602</td>\n",
+       "      <td>-0.202449</td>\n",
+       "      <td>-0.056700</td>\n",
+       "      <td>0.023556</td>\n",
+       "      <td>0.034343</td>\n",
+       "      <td>0.015555</td>\n",
+       "      <td>0.007351</td>\n",
+       "      <td>-0.228442</td>\n",
+       "      <td>-0.050515</td>\n",
+       "      <td>-0.328265</td>\n",
+       "      <td>-0.663276</td>\n",
+       "      <td>-0.105088</td>\n",
+       "      <td>-0.743126</td>\n",
+       "      <td>0.464012</td>\n",
+       "      <td>-0.617797</td>\n",
+       "      <td>-0.604733</td>\n",
+       "      <td>-0.717171</td>\n",
+       "      <td>-0.167290</td>\n",
+       "      <td>-0.111622</td>\n",
+       "      <td>0.032979</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Madrid_humidity</th>\n",
+       "      <td>-0.137092</td>\n",
+       "      <td>0.171478</td>\n",
+       "      <td>-0.019388</td>\n",
+       "      <td>0.799831</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.041878</td>\n",
+       "      <td>-0.016808</td>\n",
+       "      <td>0.374112</td>\n",
+       "      <td>-0.058518</td>\n",
+       "      <td>0.484293</td>\n",
+       "      <td>-0.125680</td>\n",
+       "      <td>-0.070508</td>\n",
+       "      <td>0.031653</td>\n",
+       "      <td>0.059958</td>\n",
+       "      <td>0.017797</td>\n",
+       "      <td>0.012571</td>\n",
+       "      <td>-0.341407</td>\n",
+       "      <td>-0.051139</td>\n",
+       "      <td>-0.291095</td>\n",
+       "      <td>-0.706989</td>\n",
+       "      <td>-0.139686</td>\n",
+       "      <td>-0.738819</td>\n",
+       "      <td>0.378980</td>\n",
+       "      <td>-0.684867</td>\n",
+       "      <td>-0.634825</td>\n",
+       "      <td>-0.802605</td>\n",
+       "      <td>-0.150536</td>\n",
+       "      <td>-0.076567</td>\n",
+       "      <td>0.047372</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Bilbao_clouds_all</th>\n",
+       "      <td>0.244001</td>\n",
+       "      <td>0.074476</td>\n",
+       "      <td>0.210524</td>\n",
+       "      <td>0.061680</td>\n",
+       "      <td>0.041878</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.031915</td>\n",
+       "      <td>0.046737</td>\n",
+       "      <td>0.094019</td>\n",
+       "      <td>0.109788</td>\n",
+       "      <td>0.075066</td>\n",
+       "      <td>0.001263</td>\n",
+       "      <td>0.080180</td>\n",
+       "      <td>0.009557</td>\n",
+       "      <td>-0.041013</td>\n",
+       "      <td>0.024339</td>\n",
+       "      <td>-0.080837</td>\n",
+       "      <td>-0.124169</td>\n",
+       "      <td>-0.033825</td>\n",
+       "      <td>-0.000299</td>\n",
+       "      <td>-0.536205</td>\n",
+       "      <td>-0.095003</td>\n",
+       "      <td>-0.129684</td>\n",
+       "      <td>-0.023171</td>\n",
+       "      <td>-0.114118</td>\n",
+       "      <td>-0.046686</td>\n",
+       "      <td>-0.127293</td>\n",
+       "      <td>-0.117452</td>\n",
+       "      <td>0.025688</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Bilbao_wind_speed</th>\n",
+       "      <td>0.377854</td>\n",
+       "      <td>0.112475</td>\n",
+       "      <td>0.386478</td>\n",
+       "      <td>-0.088180</td>\n",
+       "      <td>-0.016808</td>\n",
+       "      <td>0.031915</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.127344</td>\n",
+       "      <td>0.275317</td>\n",
+       "      <td>0.239326</td>\n",
+       "      <td>0.213420</td>\n",
+       "      <td>-0.033655</td>\n",
+       "      <td>-0.001642</td>\n",
+       "      <td>-0.026037</td>\n",
+       "      <td>-0.038246</td>\n",
+       "      <td>-0.008114</td>\n",
+       "      <td>-0.101497</td>\n",
+       "      <td>-0.003074</td>\n",
+       "      <td>-0.086691</td>\n",
+       "      <td>0.093919</td>\n",
+       "      <td>-0.031661</td>\n",
+       "      <td>0.080357</td>\n",
+       "      <td>-0.279825</td>\n",
+       "      <td>0.018967</td>\n",
+       "      <td>0.142435</td>\n",
+       "      <td>0.031245</td>\n",
+       "      <td>-0.081602</td>\n",
+       "      <td>-0.086698</td>\n",
+       "      <td>-0.008020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_clouds_all</th>\n",
+       "      <td>0.191251</td>\n",
+       "      <td>0.109314</td>\n",
+       "      <td>0.163675</td>\n",
+       "      <td>0.399436</td>\n",
+       "      <td>0.374112</td>\n",
+       "      <td>0.046737</td>\n",
+       "      <td>0.127344</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.136591</td>\n",
+       "      <td>0.552414</td>\n",
+       "      <td>0.144119</td>\n",
+       "      <td>-0.080132</td>\n",
+       "      <td>0.001718</td>\n",
+       "      <td>0.087240</td>\n",
+       "      <td>0.029194</td>\n",
+       "      <td>-0.009782</td>\n",
+       "      <td>-0.376157</td>\n",
+       "      <td>-0.099166</td>\n",
+       "      <td>-0.537924</td>\n",
+       "      <td>-0.186982</td>\n",
+       "      <td>-0.101888</td>\n",
+       "      <td>-0.208859</td>\n",
+       "      <td>0.097491</td>\n",
+       "      <td>-0.186463</td>\n",
+       "      <td>-0.152393</td>\n",
+       "      <td>-0.227094</td>\n",
+       "      <td>-0.091804</td>\n",
+       "      <td>-0.170345</td>\n",
+       "      <td>0.010582</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Barcelona_wind_speed</th>\n",
+       "      <td>0.294640</td>\n",
+       "      <td>0.116735</td>\n",
+       "      <td>0.347966</td>\n",
+       "      <td>-0.138625</td>\n",
+       "      <td>-0.058518</td>\n",
+       "      <td>0.094019</td>\n",
+       "      <td>0.275317</td>\n",
+       "      <td>0.136591</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.147652</td>\n",
+       "      <td>0.212193</td>\n",
+       "      <td>-0.017511</td>\n",
+       "      <td>0.015752</td>\n",
+       "      <td>0.058662</td>\n",
+       "      <td>-0.001722</td>\n",
+       "      <td>0.030336</td>\n",
+       "      <td>-0.106432</td>\n",
+       "      <td>-0.048004</td>\n",
+       "      <td>-0.090902</td>\n",
+       "      <td>0.121330</td>\n",
+       "      <td>-0.064746</td>\n",
+       "      <td>0.147628</td>\n",
+       "      <td>-0.249610</td>\n",
+       "      <td>0.116240</td>\n",
+       "      <td>0.120361</td>\n",
+       "      <td>0.089365</td>\n",
+       "      <td>-0.103633</td>\n",
+       "      <td>-0.122221</td>\n",
+       "      <td>-0.009699</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Madrid_clouds_all</th>\n",
+       "      <td>0.230126</td>\n",
+       "      <td>0.129917</td>\n",
+       "      <td>0.221887</td>\n",
+       "      <td>0.366602</td>\n",
+       "      <td>0.484293</td>\n",
+       "      <td>0.109788</td>\n",
+       "      <td>0.239326</td>\n",
+       "      <td>0.552414</td>\n",
+       "      <td>0.147652</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.168245</td>\n",
+       "      <td>-0.063425</td>\n",
+       "      <td>0.041997</td>\n",
+       "      <td>0.077246</td>\n",
+       "      <td>-0.000355</td>\n",
+       "      <td>0.023323</td>\n",
+       "      <td>-0.533331</td>\n",
+       "      <td>-0.119970</td>\n",
+       "      <td>-0.383770</td>\n",
+       "      <td>-0.200355</td>\n",
+       "      <td>-0.172030</td>\n",
+       "      <td>-0.240838</td>\n",
+       "      <td>0.066366</td>\n",
+       "      <td>-0.223940</td>\n",
+       "      <td>-0.174079</td>\n",
+       "      <td>-0.262908</td>\n",
+       "      <td>-0.081623</td>\n",
+       "      <td>-0.118792</td>\n",
+       "      <td>0.035940</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_wind_speed</th>\n",
+       "      <td>0.434104</td>\n",
+       "      <td>0.007634</td>\n",
+       "      <td>0.316035</td>\n",
+       "      <td>-0.202449</td>\n",
+       "      <td>-0.125680</td>\n",
+       "      <td>0.075066</td>\n",
+       "      <td>0.213420</td>\n",
+       "      <td>0.144119</td>\n",
+       "      <td>0.212193</td>\n",
+       "      <td>0.168245</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.038103</td>\n",
+       "      <td>0.046176</td>\n",
+       "      <td>0.001149</td>\n",
+       "      <td>-0.019804</td>\n",
+       "      <td>0.031472</td>\n",
+       "      <td>-0.192897</td>\n",
+       "      <td>-0.056570</td>\n",
+       "      <td>-0.143958</td>\n",
+       "      <td>0.104756</td>\n",
+       "      <td>-0.111509</td>\n",
+       "      <td>0.139573</td>\n",
+       "      <td>-0.217303</td>\n",
+       "      <td>0.085395</td>\n",
+       "      <td>0.082904</td>\n",
+       "      <td>0.108460</td>\n",
+       "      <td>-0.048433</td>\n",
+       "      <td>-0.122624</td>\n",
+       "      <td>-0.030206</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_pressure</th>\n",
+       "      <td>-0.026246</td>\n",
+       "      <td>-0.043797</td>\n",
+       "      <td>-0.010144</td>\n",
+       "      <td>-0.056700</td>\n",
+       "      <td>-0.070508</td>\n",
+       "      <td>0.001263</td>\n",
+       "      <td>-0.033655</td>\n",
+       "      <td>-0.080132</td>\n",
+       "      <td>-0.017511</td>\n",
+       "      <td>-0.063425</td>\n",
+       "      <td>0.038103</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.014270</td>\n",
+       "      <td>-0.037224</td>\n",
+       "      <td>-0.014855</td>\n",
+       "      <td>-0.015047</td>\n",
+       "      <td>0.057618</td>\n",
+       "      <td>0.032872</td>\n",
+       "      <td>0.057826</td>\n",
+       "      <td>0.072539</td>\n",
+       "      <td>0.045313</td>\n",
+       "      <td>0.058118</td>\n",
+       "      <td>0.030051</td>\n",
+       "      <td>0.085439</td>\n",
+       "      <td>0.072489</td>\n",
+       "      <td>0.091776</td>\n",
+       "      <td>0.037904</td>\n",
+       "      <td>0.013314</td>\n",
+       "      <td>0.030015</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Bilbao_snow_3h</th>\n",
+       "      <td>0.071183</td>\n",
+       "      <td>-0.005715</td>\n",
+       "      <td>0.115133</td>\n",
+       "      <td>0.023556</td>\n",
+       "      <td>0.031653</td>\n",
+       "      <td>0.080180</td>\n",
+       "      <td>-0.001642</td>\n",
+       "      <td>0.001718</td>\n",
+       "      <td>0.015752</td>\n",
+       "      <td>0.041997</td>\n",
+       "      <td>0.046176</td>\n",
+       "      <td>-0.014270</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.000391</td>\n",
+       "      <td>0.002985</td>\n",
+       "      <td>0.390939</td>\n",
+       "      <td>0.000365</td>\n",
+       "      <td>-0.033598</td>\n",
+       "      <td>0.011493</td>\n",
+       "      <td>-0.092345</td>\n",
+       "      <td>-0.107220</td>\n",
+       "      <td>-0.094889</td>\n",
+       "      <td>-0.048367</td>\n",
+       "      <td>-0.086561</td>\n",
+       "      <td>-0.096477</td>\n",
+       "      <td>-0.081209</td>\n",
+       "      <td>-0.031721</td>\n",
+       "      <td>-0.075644</td>\n",
+       "      <td>-0.055138</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_rain_3h</th>\n",
+       "      <td>0.004795</td>\n",
+       "      <td>-0.007180</td>\n",
+       "      <td>0.027637</td>\n",
+       "      <td>0.034343</td>\n",
+       "      <td>0.059958</td>\n",
+       "      <td>0.009557</td>\n",
+       "      <td>-0.026037</td>\n",
+       "      <td>0.087240</td>\n",
+       "      <td>0.058662</td>\n",
+       "      <td>0.077246</td>\n",
+       "      <td>0.001149</td>\n",
+       "      <td>-0.037224</td>\n",
+       "      <td>-0.000391</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.145740</td>\n",
+       "      <td>-0.001147</td>\n",
+       "      <td>-0.129439</td>\n",
+       "      <td>0.023488</td>\n",
+       "      <td>0.009732</td>\n",
+       "      <td>-0.062605</td>\n",
+       "      <td>-0.052032</td>\n",
+       "      <td>-0.051013</td>\n",
+       "      <td>0.031254</td>\n",
+       "      <td>-0.041804</td>\n",
+       "      <td>-0.032691</td>\n",
+       "      <td>-0.043338</td>\n",
+       "      <td>-0.032945</td>\n",
+       "      <td>-0.055265</td>\n",
+       "      <td>0.004448</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Barcelona_rain_3h</th>\n",
+       "      <td>-0.014644</td>\n",
+       "      <td>0.015736</td>\n",
+       "      <td>-0.037553</td>\n",
+       "      <td>0.015555</td>\n",
+       "      <td>0.017797</td>\n",
+       "      <td>-0.041013</td>\n",
+       "      <td>-0.038246</td>\n",
+       "      <td>0.029194</td>\n",
+       "      <td>-0.001722</td>\n",
+       "      <td>-0.000355</td>\n",
+       "      <td>-0.019804</td>\n",
+       "      <td>-0.014855</td>\n",
+       "      <td>0.002985</td>\n",
+       "      <td>0.145740</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.001905</td>\n",
+       "      <td>-0.006607</td>\n",
+       "      <td>0.026554</td>\n",
+       "      <td>-0.017497</td>\n",
+       "      <td>-0.058942</td>\n",
+       "      <td>-0.002715</td>\n",
+       "      <td>-0.039126</td>\n",
+       "      <td>0.002920</td>\n",
+       "      <td>-0.042970</td>\n",
+       "      <td>-0.043223</td>\n",
+       "      <td>-0.039565</td>\n",
+       "      <td>-0.024720</td>\n",
+       "      <td>-0.056726</td>\n",
+       "      <td>-0.021814</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Valencia_snow_3h</th>\n",
+       "      <td>0.021660</td>\n",
+       "      <td>-0.003976</td>\n",
+       "      <td>0.058629</td>\n",
+       "      <td>0.007351</td>\n",
+       "      <td>0.012571</td>\n",
+       "      <td>0.024339</td>\n",
+       "      <td>-0.008114</td>\n",
+       "      <td>-0.009782</td>\n",
+       "      <td>0.030336</td>\n",
+       "      <td>0.023323</td>\n",
+       "      <td>0.031472</td>\n",
+       "      <td>-0.015047</td>\n",
+       "      <td>0.390939</td>\n",
+       "      <td>-0.001147</td>\n",
+       "      <td>-0.001905</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.006523</td>\n",
+       "      <td>-0.005456</td>\n",
+       "      <td>0.006099</td>\n",
+       "      <td>-0.027452</td>\n",
+       "      <td>-0.033581</td>\n",
+       "      <td>-0.025473</td>\n",
+       "      <td>-0.019085</td>\n",
+       "      <td>-0.029135</td>\n",
+       "      <td>-0.031726</td>\n",
+       "      <td>-0.023734</td>\n",
+       "      <td>-0.021633</td>\n",
+       "      <td>-0.022720</td>\n",
+       "      <td>-0.023046</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Madrid_weather_id</th>\n",
+       "      <td>-0.169358</td>\n",
+       "      <td>-0.027027</td>\n",
+       "      <td>-0.099056</td>\n",
+       "      <td>-0.228442</td>\n",
+       "      <td>-0.341407</td>\n",
+       "      <td>-0.080837</td>\n",
+       "      <td>-0.101497</td>\n",
+       "      <td>-0.376157</td>\n",
+       "      <td>-0.106432</td>\n",
+       "      <td>-0.533331</td>\n",
+       "      <td>-0.192897</td>\n",
+       "      <td>0.057618</td>\n",
+       "      <td>0.000365</td>\n",
+       "      <td>-0.129439</td>\n",
+       "      <td>-0.006607</td>\n",
+       "      <td>0.006523</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.137262</td>\n",
+       "      <td>0.401143</td>\n",
+       "      <td>0.095043</td>\n",
+       "      <td>0.160212</td>\n",
+       "      <td>0.116834</td>\n",
+       "      <td>-0.097104</td>\n",
+       "      <td>0.085587</td>\n",
+       "      <td>0.068572</td>\n",
+       "      <td>0.136829</td>\n",
+       "      <td>0.030868</td>\n",
+       "      <td>0.068856</td>\n",
+       "      <td>-0.031751</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Barcelona_weather_id</th>\n",
+       "      <td>-0.099582</td>\n",
+       "      <td>-0.000043</td>\n",
+       "      <td>-0.037605</td>\n",
+       "      <td>-0.050515</td>\n",
+       "      <td>-0.051139</td>\n",
+       "      <td>-0.124169</td>\n",
+       "      <td>-0.003074</td>\n",
+       "      <td>-0.099166</td>\n",
+       "      <td>-0.048004</td>\n",
+       "      <td>-0.119970</td>\n",
+       "      <td>-0.056570</td>\n",
+       "      <td>0.032872</td>\n",
+       "      <td>-0.033598</td>\n",
+       "      <td>0.023488</td>\n",
+       "      <td>0.026554</td>\n",
+       "      <td>-0.005456</td>\n",
+       "      <td>0.137262</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.123593</td>\n",
+       "      <td>0.031316</td>\n",
+       "      <td>0.119813</td>\n",
+       "      <td>0.014065</td>\n",
+       "      <td>-0.096343</td>\n",
+       "      <td>0.029239</td>\n",
+       "      <td>0.053303</td>\n",
+       "      <td>0.025671</td>\n",
+       "      <td>0.063868</td>\n",
+       "      <td>0.025352</td>\n",
+       "      <td>-0.035885</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_weather_id</th>\n",
+       "      <td>-0.120014</td>\n",
+       "      <td>-0.020651</td>\n",
+       "      <td>-0.069092</td>\n",
+       "      <td>-0.328265</td>\n",
+       "      <td>-0.291095</td>\n",
+       "      <td>-0.033825</td>\n",
+       "      <td>-0.086691</td>\n",
+       "      <td>-0.537924</td>\n",
+       "      <td>-0.090902</td>\n",
+       "      <td>-0.383770</td>\n",
+       "      <td>-0.143958</td>\n",
+       "      <td>0.057826</td>\n",
+       "      <td>0.011493</td>\n",
+       "      <td>0.009732</td>\n",
+       "      <td>-0.017497</td>\n",
+       "      <td>0.006099</td>\n",
+       "      <td>0.401143</td>\n",
+       "      <td>0.123593</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.170912</td>\n",
+       "      <td>0.074054</td>\n",
+       "      <td>0.166098</td>\n",
+       "      <td>-0.132907</td>\n",
+       "      <td>0.168608</td>\n",
+       "      <td>0.134535</td>\n",
+       "      <td>0.185768</td>\n",
+       "      <td>0.061104</td>\n",
+       "      <td>0.100786</td>\n",
+       "      <td>0.000676</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Valencia_temp</th>\n",
+       "      <td>0.128726</td>\n",
+       "      <td>-0.084541</td>\n",
+       "      <td>0.072366</td>\n",
+       "      <td>-0.663276</td>\n",
+       "      <td>-0.706989</td>\n",
+       "      <td>-0.000299</td>\n",
+       "      <td>0.093919</td>\n",
+       "      <td>-0.186982</td>\n",
+       "      <td>0.121330</td>\n",
+       "      <td>-0.200355</td>\n",
+       "      <td>0.104756</td>\n",
+       "      <td>0.072539</td>\n",
+       "      <td>-0.092345</td>\n",
+       "      <td>-0.062605</td>\n",
+       "      <td>-0.058942</td>\n",
+       "      <td>-0.027452</td>\n",
+       "      <td>0.095043</td>\n",
+       "      <td>0.031316</td>\n",
+       "      <td>0.170912</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.106095</td>\n",
+       "      <td>0.887040</td>\n",
+       "      <td>-0.413654</td>\n",
+       "      <td>0.914601</td>\n",
+       "      <td>0.854892</td>\n",
+       "      <td>0.915753</td>\n",
+       "      <td>0.173225</td>\n",
+       "      <td>0.216464</td>\n",
+       "      <td>-0.000728</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Bilbao_weather_id</th>\n",
+       "      <td>-0.238128</td>\n",
+       "      <td>-0.099664</td>\n",
+       "      <td>-0.201379</td>\n",
+       "      <td>-0.105088</td>\n",
+       "      <td>-0.139686</td>\n",
+       "      <td>-0.536205</td>\n",
+       "      <td>-0.031661</td>\n",
+       "      <td>-0.101888</td>\n",
+       "      <td>-0.064746</td>\n",
+       "      <td>-0.172030</td>\n",
+       "      <td>-0.111509</td>\n",
+       "      <td>0.045313</td>\n",
+       "      <td>-0.107220</td>\n",
+       "      <td>-0.052032</td>\n",
+       "      <td>-0.002715</td>\n",
+       "      <td>-0.033581</td>\n",
+       "      <td>0.160212</td>\n",
+       "      <td>0.119813</td>\n",
+       "      <td>0.074054</td>\n",
+       "      <td>0.106095</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.190360</td>\n",
+       "      <td>0.114838</td>\n",
+       "      <td>0.128188</td>\n",
+       "      <td>0.190635</td>\n",
+       "      <td>0.143126</td>\n",
+       "      <td>0.145875</td>\n",
+       "      <td>0.141738</td>\n",
+       "      <td>-0.017562</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Seville_temp</th>\n",
+       "      <td>0.090861</td>\n",
+       "      <td>-0.151280</td>\n",
+       "      <td>-0.008508</td>\n",
+       "      <td>-0.743126</td>\n",
+       "      <td>-0.738819</td>\n",
+       "      <td>-0.095003</td>\n",
+       "      <td>0.080357</td>\n",
+       "      <td>-0.208859</td>\n",
+       "      <td>0.147628</td>\n",
+       "      <td>-0.240838</td>\n",
+       "      <td>0.139573</td>\n",
+       "      <td>0.058118</td>\n",
+       "      <td>-0.094889</td>\n",
+       "      <td>-0.051013</td>\n",
+       "      <td>-0.039126</td>\n",
+       "      <td>-0.025473</td>\n",
+       "      <td>0.116834</td>\n",
+       "      <td>0.014065</td>\n",
+       "      <td>0.166098</td>\n",
+       "      <td>0.887040</td>\n",
+       "      <td>0.190360</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.281993</td>\n",
+       "      <td>0.852651</td>\n",
+       "      <td>0.839014</td>\n",
+       "      <td>0.917075</td>\n",
+       "      <td>0.159343</td>\n",
+       "      <td>0.213623</td>\n",
+       "      <td>-0.017066</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Valencia_humidity</th>\n",
+       "      <td>-0.285787</td>\n",
+       "      <td>-0.198984</td>\n",
+       "      <td>-0.413017</td>\n",
+       "      <td>0.464012</td>\n",
+       "      <td>0.378980</td>\n",
+       "      <td>-0.129684</td>\n",
+       "      <td>-0.279825</td>\n",
+       "      <td>0.097491</td>\n",
+       "      <td>-0.249610</td>\n",
+       "      <td>0.066366</td>\n",
+       "      <td>-0.217303</td>\n",
+       "      <td>0.030051</td>\n",
+       "      <td>-0.048367</td>\n",
+       "      <td>0.031254</td>\n",
+       "      <td>0.002920</td>\n",
+       "      <td>-0.019085</td>\n",
+       "      <td>-0.097104</td>\n",
+       "      <td>-0.096343</td>\n",
+       "      <td>-0.132907</td>\n",
+       "      <td>-0.413654</td>\n",
+       "      <td>0.114838</td>\n",
+       "      <td>-0.281993</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>-0.247168</td>\n",
+       "      <td>-0.260946</td>\n",
+       "      <td>-0.261356</td>\n",
+       "      <td>0.043140</td>\n",
+       "      <td>0.162713</td>\n",
+       "      <td>0.047823</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Barcelona_temp</th>\n",
+       "      <td>0.080133</td>\n",
+       "      <td>-0.113788</td>\n",
+       "      <td>-0.021456</td>\n",
+       "      <td>-0.617797</td>\n",
+       "      <td>-0.684867</td>\n",
+       "      <td>-0.023171</td>\n",
+       "      <td>0.018967</td>\n",
+       "      <td>-0.186463</td>\n",
+       "      <td>0.116240</td>\n",
+       "      <td>-0.223940</td>\n",
+       "      <td>0.085395</td>\n",
+       "      <td>0.085439</td>\n",
+       "      <td>-0.086561</td>\n",
+       "      <td>-0.041804</td>\n",
+       "      <td>-0.042970</td>\n",
+       "      <td>-0.029135</td>\n",
+       "      <td>0.085587</td>\n",
+       "      <td>0.029239</td>\n",
+       "      <td>0.168608</td>\n",
+       "      <td>0.914601</td>\n",
+       "      <td>0.128188</td>\n",
+       "      <td>0.852651</td>\n",
+       "      <td>-0.247168</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.865705</td>\n",
+       "      <td>0.903143</td>\n",
+       "      <td>0.182673</td>\n",
+       "      <td>0.203184</td>\n",
+       "      <td>-0.001659</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Bilbao_temp</th>\n",
+       "      <td>0.060467</td>\n",
+       "      <td>-0.099050</td>\n",
+       "      <td>-0.022676</td>\n",
+       "      <td>-0.604733</td>\n",
+       "      <td>-0.634825</td>\n",
+       "      <td>-0.114118</td>\n",
+       "      <td>0.142435</td>\n",
+       "      <td>-0.152393</td>\n",
+       "      <td>0.120361</td>\n",
+       "      <td>-0.174079</td>\n",
+       "      <td>0.082904</td>\n",
+       "      <td>0.072489</td>\n",
+       "      <td>-0.096477</td>\n",
+       "      <td>-0.032691</td>\n",
+       "      <td>-0.043223</td>\n",
+       "      <td>-0.031726</td>\n",
+       "      <td>0.068572</td>\n",
+       "      <td>0.053303</td>\n",
+       "      <td>0.134535</td>\n",
+       "      <td>0.854892</td>\n",
+       "      <td>0.190635</td>\n",
+       "      <td>0.839014</td>\n",
+       "      <td>-0.260946</td>\n",
+       "      <td>0.865705</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.875271</td>\n",
+       "      <td>0.176411</td>\n",
+       "      <td>0.239443</td>\n",
+       "      <td>0.020639</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Madrid_temp</th>\n",
+       "      <td>0.109572</td>\n",
+       "      <td>-0.166092</td>\n",
+       "      <td>-0.011982</td>\n",
+       "      <td>-0.717171</td>\n",
+       "      <td>-0.802605</td>\n",
+       "      <td>-0.046686</td>\n",
+       "      <td>0.031245</td>\n",
+       "      <td>-0.227094</td>\n",
+       "      <td>0.089365</td>\n",
+       "      <td>-0.262908</td>\n",
+       "      <td>0.108460</td>\n",
+       "      <td>0.091776</td>\n",
+       "      <td>-0.081209</td>\n",
+       "      <td>-0.043338</td>\n",
+       "      <td>-0.039565</td>\n",
+       "      <td>-0.023734</td>\n",
+       "      <td>0.136829</td>\n",
+       "      <td>0.025671</td>\n",
+       "      <td>0.185768</td>\n",
+       "      <td>0.915753</td>\n",
+       "      <td>0.143126</td>\n",
+       "      <td>0.917075</td>\n",
+       "      <td>-0.261356</td>\n",
+       "      <td>0.903143</td>\n",
+       "      <td>0.875271</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.186036</td>\n",
+       "      <td>0.182860</td>\n",
+       "      <td>0.000861</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>load_shortfall_3h</th>\n",
+       "      <td>-0.150981</td>\n",
+       "      <td>-0.110849</td>\n",
+       "      <td>-0.142791</td>\n",
+       "      <td>-0.167290</td>\n",
+       "      <td>-0.150536</td>\n",
+       "      <td>-0.127293</td>\n",
+       "      <td>-0.081602</td>\n",
+       "      <td>-0.091804</td>\n",
+       "      <td>-0.103633</td>\n",
+       "      <td>-0.081623</td>\n",
+       "      <td>-0.048433</td>\n",
+       "      <td>0.037904</td>\n",
+       "      <td>-0.031721</td>\n",
+       "      <td>-0.032945</td>\n",
+       "      <td>-0.024720</td>\n",
+       "      <td>-0.021633</td>\n",
+       "      <td>0.030868</td>\n",
+       "      <td>0.063868</td>\n",
+       "      <td>0.061104</td>\n",
+       "      <td>0.173225</td>\n",
+       "      <td>0.145875</td>\n",
+       "      <td>0.159343</td>\n",
+       "      <td>0.043140</td>\n",
+       "      <td>0.182673</td>\n",
+       "      <td>0.176411</td>\n",
+       "      <td>0.186036</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.199048</td>\n",
+       "      <td>0.092116</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>month</th>\n",
+       "      <td>-0.237445</td>\n",
+       "      <td>-0.087571</td>\n",
+       "      <td>-0.237156</td>\n",
+       "      <td>-0.111622</td>\n",
+       "      <td>-0.076567</td>\n",
+       "      <td>-0.117452</td>\n",
+       "      <td>-0.086698</td>\n",
+       "      <td>-0.170345</td>\n",
+       "      <td>-0.122221</td>\n",
+       "      <td>-0.118792</td>\n",
+       "      <td>-0.122624</td>\n",
+       "      <td>0.013314</td>\n",
+       "      <td>-0.075644</td>\n",
+       "      <td>-0.055265</td>\n",
+       "      <td>-0.056726</td>\n",
+       "      <td>-0.022720</td>\n",
+       "      <td>0.068856</td>\n",
+       "      <td>0.025352</td>\n",
+       "      <td>0.100786</td>\n",
+       "      <td>0.216464</td>\n",
+       "      <td>0.141738</td>\n",
+       "      <td>0.213623</td>\n",
+       "      <td>0.162713</td>\n",
+       "      <td>0.203184</td>\n",
+       "      <td>0.239443</td>\n",
+       "      <td>0.182860</td>\n",
+       "      <td>0.199048</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.008826</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>day</th>\n",
+       "      <td>-0.029954</td>\n",
+       "      <td>-0.025467</td>\n",
+       "      <td>-0.000340</td>\n",
+       "      <td>0.032979</td>\n",
+       "      <td>0.047372</td>\n",
+       "      <td>0.025688</td>\n",
+       "      <td>-0.008020</td>\n",
+       "      <td>0.010582</td>\n",
+       "      <td>-0.009699</td>\n",
+       "      <td>0.035940</td>\n",
+       "      <td>-0.030206</td>\n",
+       "      <td>0.030015</td>\n",
+       "      <td>-0.055138</td>\n",
+       "      <td>0.004448</td>\n",
+       "      <td>-0.021814</td>\n",
+       "      <td>-0.023046</td>\n",
+       "      <td>-0.031751</td>\n",
+       "      <td>-0.035885</td>\n",
+       "      <td>0.000676</td>\n",
+       "      <td>-0.000728</td>\n",
+       "      <td>-0.017562</td>\n",
+       "      <td>-0.017066</td>\n",
+       "      <td>0.047823</td>\n",
+       "      <td>-0.001659</td>\n",
+       "      <td>0.020639</td>\n",
+       "      <td>0.000861</td>\n",
+       "      <td>0.092116</td>\n",
+       "      <td>0.008826</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                      Madrid_wind_speed  Valencia_wind_deg  \\\n",
+       "Madrid_wind_speed              1.000000           0.104954   \n",
+       "Valencia_wind_deg              0.104954           1.000000   \n",
+       "Valencia_wind_speed            0.513092           0.204874   \n",
+       "Seville_humidity              -0.117892           0.141594   \n",
+       "Madrid_humidity               -0.137092           0.171478   \n",
+       "Bilbao_clouds_all              0.244001           0.074476   \n",
+       "Bilbao_wind_speed              0.377854           0.112475   \n",
+       "Seville_clouds_all             0.191251           0.109314   \n",
+       "Barcelona_wind_speed           0.294640           0.116735   \n",
+       "Madrid_clouds_all              0.230126           0.129917   \n",
+       "Seville_wind_speed             0.434104           0.007634   \n",
+       "Seville_pressure              -0.026246          -0.043797   \n",
+       "Bilbao_snow_3h                 0.071183          -0.005715   \n",
+       "Seville_rain_3h                0.004795          -0.007180   \n",
+       "Barcelona_rain_3h             -0.014644           0.015736   \n",
+       "Valencia_snow_3h               0.021660          -0.003976   \n",
+       "Madrid_weather_id             -0.169358          -0.027027   \n",
+       "Barcelona_weather_id          -0.099582          -0.000043   \n",
+       "Seville_weather_id            -0.120014          -0.020651   \n",
+       "Valencia_temp                  0.128726          -0.084541   \n",
+       "Bilbao_weather_id             -0.238128          -0.099664   \n",
+       "Seville_temp                   0.090861          -0.151280   \n",
+       "Valencia_humidity             -0.285787          -0.198984   \n",
+       "Barcelona_temp                 0.080133          -0.113788   \n",
+       "Bilbao_temp                    0.060467          -0.099050   \n",
+       "Madrid_temp                    0.109572          -0.166092   \n",
+       "load_shortfall_3h             -0.150981          -0.110849   \n",
+       "month                         -0.237445          -0.087571   \n",
+       "day                           -0.029954          -0.025467   \n",
+       "\n",
+       "                      Valencia_wind_speed  Seville_humidity  Madrid_humidity  \\\n",
+       "Madrid_wind_speed                0.513092         -0.117892        -0.137092   \n",
+       "Valencia_wind_deg                0.204874          0.141594         0.171478   \n",
+       "Valencia_wind_speed              1.000000         -0.075227        -0.019388   \n",
+       "Seville_humidity                -0.075227          1.000000         0.799831   \n",
+       "Madrid_humidity                 -0.019388          0.799831         1.000000   \n",
+       "Bilbao_clouds_all                0.210524          0.061680         0.041878   \n",
+       "Bilbao_wind_speed                0.386478         -0.088180        -0.016808   \n",
+       "Seville_clouds_all               0.163675          0.399436         0.374112   \n",
+       "Barcelona_wind_speed             0.347966         -0.138625        -0.058518   \n",
+       "Madrid_clouds_all                0.221887          0.366602         0.484293   \n",
+       "Seville_wind_speed               0.316035         -0.202449        -0.125680   \n",
+       "Seville_pressure                -0.010144         -0.056700        -0.070508   \n",
+       "Bilbao_snow_3h                   0.115133          0.023556         0.031653   \n",
+       "Seville_rain_3h                  0.027637          0.034343         0.059958   \n",
+       "Barcelona_rain_3h               -0.037553          0.015555         0.017797   \n",
+       "Valencia_snow_3h                 0.058629          0.007351         0.012571   \n",
+       "Madrid_weather_id               -0.099056         -0.228442        -0.341407   \n",
+       "Barcelona_weather_id            -0.037605         -0.050515        -0.051139   \n",
+       "Seville_weather_id              -0.069092         -0.328265        -0.291095   \n",
+       "Valencia_temp                    0.072366         -0.663276        -0.706989   \n",
+       "Bilbao_weather_id               -0.201379         -0.105088        -0.139686   \n",
+       "Seville_temp                    -0.008508         -0.743126        -0.738819   \n",
+       "Valencia_humidity               -0.413017          0.464012         0.378980   \n",
+       "Barcelona_temp                  -0.021456         -0.617797        -0.684867   \n",
+       "Bilbao_temp                     -0.022676         -0.604733        -0.634825   \n",
+       "Madrid_temp                     -0.011982         -0.717171        -0.802605   \n",
+       "load_shortfall_3h               -0.142791         -0.167290        -0.150536   \n",
+       "month                           -0.237156         -0.111622        -0.076567   \n",
+       "day                             -0.000340          0.032979         0.047372   \n",
+       "\n",
+       "                      Bilbao_clouds_all  Bilbao_wind_speed  \\\n",
+       "Madrid_wind_speed              0.244001           0.377854   \n",
+       "Valencia_wind_deg              0.074476           0.112475   \n",
+       "Valencia_wind_speed            0.210524           0.386478   \n",
+       "Seville_humidity               0.061680          -0.088180   \n",
+       "Madrid_humidity                0.041878          -0.016808   \n",
+       "Bilbao_clouds_all              1.000000           0.031915   \n",
+       "Bilbao_wind_speed              0.031915           1.000000   \n",
+       "Seville_clouds_all             0.046737           0.127344   \n",
+       "Barcelona_wind_speed           0.094019           0.275317   \n",
+       "Madrid_clouds_all              0.109788           0.239326   \n",
+       "Seville_wind_speed             0.075066           0.213420   \n",
+       "Seville_pressure               0.001263          -0.033655   \n",
+       "Bilbao_snow_3h                 0.080180          -0.001642   \n",
+       "Seville_rain_3h                0.009557          -0.026037   \n",
+       "Barcelona_rain_3h             -0.041013          -0.038246   \n",
+       "Valencia_snow_3h               0.024339          -0.008114   \n",
+       "Madrid_weather_id             -0.080837          -0.101497   \n",
+       "Barcelona_weather_id          -0.124169          -0.003074   \n",
+       "Seville_weather_id            -0.033825          -0.086691   \n",
+       "Valencia_temp                 -0.000299           0.093919   \n",
+       "Bilbao_weather_id             -0.536205          -0.031661   \n",
+       "Seville_temp                  -0.095003           0.080357   \n",
+       "Valencia_humidity             -0.129684          -0.279825   \n",
+       "Barcelona_temp                -0.023171           0.018967   \n",
+       "Bilbao_temp                   -0.114118           0.142435   \n",
+       "Madrid_temp                   -0.046686           0.031245   \n",
+       "load_shortfall_3h             -0.127293          -0.081602   \n",
+       "month                         -0.117452          -0.086698   \n",
+       "day                            0.025688          -0.008020   \n",
+       "\n",
+       "                      Seville_clouds_all  Barcelona_wind_speed  \\\n",
+       "Madrid_wind_speed               0.191251              0.294640   \n",
+       "Valencia_wind_deg               0.109314              0.116735   \n",
+       "Valencia_wind_speed             0.163675              0.347966   \n",
+       "Seville_humidity                0.399436             -0.138625   \n",
+       "Madrid_humidity                 0.374112             -0.058518   \n",
+       "Bilbao_clouds_all               0.046737              0.094019   \n",
+       "Bilbao_wind_speed               0.127344              0.275317   \n",
+       "Seville_clouds_all              1.000000              0.136591   \n",
+       "Barcelona_wind_speed            0.136591              1.000000   \n",
+       "Madrid_clouds_all               0.552414              0.147652   \n",
+       "Seville_wind_speed              0.144119              0.212193   \n",
+       "Seville_pressure               -0.080132             -0.017511   \n",
+       "Bilbao_snow_3h                  0.001718              0.015752   \n",
+       "Seville_rain_3h                 0.087240              0.058662   \n",
+       "Barcelona_rain_3h               0.029194             -0.001722   \n",
+       "Valencia_snow_3h               -0.009782              0.030336   \n",
+       "Madrid_weather_id              -0.376157             -0.106432   \n",
+       "Barcelona_weather_id           -0.099166             -0.048004   \n",
+       "Seville_weather_id             -0.537924             -0.090902   \n",
+       "Valencia_temp                  -0.186982              0.121330   \n",
+       "Bilbao_weather_id              -0.101888             -0.064746   \n",
+       "Seville_temp                   -0.208859              0.147628   \n",
+       "Valencia_humidity               0.097491             -0.249610   \n",
+       "Barcelona_temp                 -0.186463              0.116240   \n",
+       "Bilbao_temp                    -0.152393              0.120361   \n",
+       "Madrid_temp                    -0.227094              0.089365   \n",
+       "load_shortfall_3h              -0.091804             -0.103633   \n",
+       "month                          -0.170345             -0.122221   \n",
+       "day                             0.010582             -0.009699   \n",
+       "\n",
+       "                      Madrid_clouds_all  Seville_wind_speed  Seville_pressure  \\\n",
+       "Madrid_wind_speed              0.230126            0.434104         -0.026246   \n",
+       "Valencia_wind_deg              0.129917            0.007634         -0.043797   \n",
+       "Valencia_wind_speed            0.221887            0.316035         -0.010144   \n",
+       "Seville_humidity               0.366602           -0.202449         -0.056700   \n",
+       "Madrid_humidity                0.484293           -0.125680         -0.070508   \n",
+       "Bilbao_clouds_all              0.109788            0.075066          0.001263   \n",
+       "Bilbao_wind_speed              0.239326            0.213420         -0.033655   \n",
+       "Seville_clouds_all             0.552414            0.144119         -0.080132   \n",
+       "Barcelona_wind_speed           0.147652            0.212193         -0.017511   \n",
+       "Madrid_clouds_all              1.000000            0.168245         -0.063425   \n",
+       "Seville_wind_speed             0.168245            1.000000          0.038103   \n",
+       "Seville_pressure              -0.063425            0.038103          1.000000   \n",
+       "Bilbao_snow_3h                 0.041997            0.046176         -0.014270   \n",
+       "Seville_rain_3h                0.077246            0.001149         -0.037224   \n",
+       "Barcelona_rain_3h             -0.000355           -0.019804         -0.014855   \n",
+       "Valencia_snow_3h               0.023323            0.031472         -0.015047   \n",
+       "Madrid_weather_id             -0.533331           -0.192897          0.057618   \n",
+       "Barcelona_weather_id          -0.119970           -0.056570          0.032872   \n",
+       "Seville_weather_id            -0.383770           -0.143958          0.057826   \n",
+       "Valencia_temp                 -0.200355            0.104756          0.072539   \n",
+       "Bilbao_weather_id             -0.172030           -0.111509          0.045313   \n",
+       "Seville_temp                  -0.240838            0.139573          0.058118   \n",
+       "Valencia_humidity              0.066366           -0.217303          0.030051   \n",
+       "Barcelona_temp                -0.223940            0.085395          0.085439   \n",
+       "Bilbao_temp                   -0.174079            0.082904          0.072489   \n",
+       "Madrid_temp                   -0.262908            0.108460          0.091776   \n",
+       "load_shortfall_3h             -0.081623           -0.048433          0.037904   \n",
+       "month                         -0.118792           -0.122624          0.013314   \n",
+       "day                            0.035940           -0.030206          0.030015   \n",
+       "\n",
+       "                      Bilbao_snow_3h  Seville_rain_3h  Barcelona_rain_3h  \\\n",
+       "Madrid_wind_speed           0.071183         0.004795          -0.014644   \n",
+       "Valencia_wind_deg          -0.005715        -0.007180           0.015736   \n",
+       "Valencia_wind_speed         0.115133         0.027637          -0.037553   \n",
+       "Seville_humidity            0.023556         0.034343           0.015555   \n",
+       "Madrid_humidity             0.031653         0.059958           0.017797   \n",
+       "Bilbao_clouds_all           0.080180         0.009557          -0.041013   \n",
+       "Bilbao_wind_speed          -0.001642        -0.026037          -0.038246   \n",
+       "Seville_clouds_all          0.001718         0.087240           0.029194   \n",
+       "Barcelona_wind_speed        0.015752         0.058662          -0.001722   \n",
+       "Madrid_clouds_all           0.041997         0.077246          -0.000355   \n",
+       "Seville_wind_speed          0.046176         0.001149          -0.019804   \n",
+       "Seville_pressure           -0.014270        -0.037224          -0.014855   \n",
+       "Bilbao_snow_3h              1.000000        -0.000391           0.002985   \n",
+       "Seville_rain_3h            -0.000391         1.000000           0.145740   \n",
+       "Barcelona_rain_3h           0.002985         0.145740           1.000000   \n",
+       "Valencia_snow_3h            0.390939        -0.001147          -0.001905   \n",
+       "Madrid_weather_id           0.000365        -0.129439          -0.006607   \n",
+       "Barcelona_weather_id       -0.033598         0.023488           0.026554   \n",
+       "Seville_weather_id          0.011493         0.009732          -0.017497   \n",
+       "Valencia_temp              -0.092345        -0.062605          -0.058942   \n",
+       "Bilbao_weather_id          -0.107220        -0.052032          -0.002715   \n",
+       "Seville_temp               -0.094889        -0.051013          -0.039126   \n",
+       "Valencia_humidity          -0.048367         0.031254           0.002920   \n",
+       "Barcelona_temp             -0.086561        -0.041804          -0.042970   \n",
+       "Bilbao_temp                -0.096477        -0.032691          -0.043223   \n",
+       "Madrid_temp                -0.081209        -0.043338          -0.039565   \n",
+       "load_shortfall_3h          -0.031721        -0.032945          -0.024720   \n",
+       "month                      -0.075644        -0.055265          -0.056726   \n",
+       "day                        -0.055138         0.004448          -0.021814   \n",
+       "\n",
+       "                      Valencia_snow_3h  Madrid_weather_id  \\\n",
+       "Madrid_wind_speed             0.021660          -0.169358   \n",
+       "Valencia_wind_deg            -0.003976          -0.027027   \n",
+       "Valencia_wind_speed           0.058629          -0.099056   \n",
+       "Seville_humidity              0.007351          -0.228442   \n",
+       "Madrid_humidity               0.012571          -0.341407   \n",
+       "Bilbao_clouds_all             0.024339          -0.080837   \n",
+       "Bilbao_wind_speed            -0.008114          -0.101497   \n",
+       "Seville_clouds_all           -0.009782          -0.376157   \n",
+       "Barcelona_wind_speed          0.030336          -0.106432   \n",
+       "Madrid_clouds_all             0.023323          -0.533331   \n",
+       "Seville_wind_speed            0.031472          -0.192897   \n",
+       "Seville_pressure             -0.015047           0.057618   \n",
+       "Bilbao_snow_3h                0.390939           0.000365   \n",
+       "Seville_rain_3h              -0.001147          -0.129439   \n",
+       "Barcelona_rain_3h            -0.001905          -0.006607   \n",
+       "Valencia_snow_3h              1.000000           0.006523   \n",
+       "Madrid_weather_id             0.006523           1.000000   \n",
+       "Barcelona_weather_id         -0.005456           0.137262   \n",
+       "Seville_weather_id            0.006099           0.401143   \n",
+       "Valencia_temp                -0.027452           0.095043   \n",
+       "Bilbao_weather_id            -0.033581           0.160212   \n",
+       "Seville_temp                 -0.025473           0.116834   \n",
+       "Valencia_humidity            -0.019085          -0.097104   \n",
+       "Barcelona_temp               -0.029135           0.085587   \n",
+       "Bilbao_temp                  -0.031726           0.068572   \n",
+       "Madrid_temp                  -0.023734           0.136829   \n",
+       "load_shortfall_3h            -0.021633           0.030868   \n",
+       "month                        -0.022720           0.068856   \n",
+       "day                          -0.023046          -0.031751   \n",
+       "\n",
+       "                      Barcelona_weather_id  Seville_weather_id  Valencia_temp  \\\n",
+       "Madrid_wind_speed                -0.099582           -0.120014       0.128726   \n",
+       "Valencia_wind_deg                -0.000043           -0.020651      -0.084541   \n",
+       "Valencia_wind_speed              -0.037605           -0.069092       0.072366   \n",
+       "Seville_humidity                 -0.050515           -0.328265      -0.663276   \n",
+       "Madrid_humidity                  -0.051139           -0.291095      -0.706989   \n",
+       "Bilbao_clouds_all                -0.124169           -0.033825      -0.000299   \n",
+       "Bilbao_wind_speed                -0.003074           -0.086691       0.093919   \n",
+       "Seville_clouds_all               -0.099166           -0.537924      -0.186982   \n",
+       "Barcelona_wind_speed             -0.048004           -0.090902       0.121330   \n",
+       "Madrid_clouds_all                -0.119970           -0.383770      -0.200355   \n",
+       "Seville_wind_speed               -0.056570           -0.143958       0.104756   \n",
+       "Seville_pressure                  0.032872            0.057826       0.072539   \n",
+       "Bilbao_snow_3h                   -0.033598            0.011493      -0.092345   \n",
+       "Seville_rain_3h                   0.023488            0.009732      -0.062605   \n",
+       "Barcelona_rain_3h                 0.026554           -0.017497      -0.058942   \n",
+       "Valencia_snow_3h                 -0.005456            0.006099      -0.027452   \n",
+       "Madrid_weather_id                 0.137262            0.401143       0.095043   \n",
+       "Barcelona_weather_id              1.000000            0.123593       0.031316   \n",
+       "Seville_weather_id                0.123593            1.000000       0.170912   \n",
+       "Valencia_temp                     0.031316            0.170912       1.000000   \n",
+       "Bilbao_weather_id                 0.119813            0.074054       0.106095   \n",
+       "Seville_temp                      0.014065            0.166098       0.887040   \n",
+       "Valencia_humidity                -0.096343           -0.132907      -0.413654   \n",
+       "Barcelona_temp                    0.029239            0.168608       0.914601   \n",
+       "Bilbao_temp                       0.053303            0.134535       0.854892   \n",
+       "Madrid_temp                       0.025671            0.185768       0.915753   \n",
+       "load_shortfall_3h                 0.063868            0.061104       0.173225   \n",
+       "month                             0.025352            0.100786       0.216464   \n",
+       "day                              -0.035885            0.000676      -0.000728   \n",
+       "\n",
+       "                      Bilbao_weather_id  Seville_temp  Valencia_humidity  \\\n",
+       "Madrid_wind_speed             -0.238128      0.090861          -0.285787   \n",
+       "Valencia_wind_deg             -0.099664     -0.151280          -0.198984   \n",
+       "Valencia_wind_speed           -0.201379     -0.008508          -0.413017   \n",
+       "Seville_humidity              -0.105088     -0.743126           0.464012   \n",
+       "Madrid_humidity               -0.139686     -0.738819           0.378980   \n",
+       "Bilbao_clouds_all             -0.536205     -0.095003          -0.129684   \n",
+       "Bilbao_wind_speed             -0.031661      0.080357          -0.279825   \n",
+       "Seville_clouds_all            -0.101888     -0.208859           0.097491   \n",
+       "Barcelona_wind_speed          -0.064746      0.147628          -0.249610   \n",
+       "Madrid_clouds_all             -0.172030     -0.240838           0.066366   \n",
+       "Seville_wind_speed            -0.111509      0.139573          -0.217303   \n",
+       "Seville_pressure               0.045313      0.058118           0.030051   \n",
+       "Bilbao_snow_3h                -0.107220     -0.094889          -0.048367   \n",
+       "Seville_rain_3h               -0.052032     -0.051013           0.031254   \n",
+       "Barcelona_rain_3h             -0.002715     -0.039126           0.002920   \n",
+       "Valencia_snow_3h              -0.033581     -0.025473          -0.019085   \n",
+       "Madrid_weather_id              0.160212      0.116834          -0.097104   \n",
+       "Barcelona_weather_id           0.119813      0.014065          -0.096343   \n",
+       "Seville_weather_id             0.074054      0.166098          -0.132907   \n",
+       "Valencia_temp                  0.106095      0.887040          -0.413654   \n",
+       "Bilbao_weather_id              1.000000      0.190360           0.114838   \n",
+       "Seville_temp                   0.190360      1.000000          -0.281993   \n",
+       "Valencia_humidity              0.114838     -0.281993           1.000000   \n",
+       "Barcelona_temp                 0.128188      0.852651          -0.247168   \n",
+       "Bilbao_temp                    0.190635      0.839014          -0.260946   \n",
+       "Madrid_temp                    0.143126      0.917075          -0.261356   \n",
+       "load_shortfall_3h              0.145875      0.159343           0.043140   \n",
+       "month                          0.141738      0.213623           0.162713   \n",
+       "day                           -0.017562     -0.017066           0.047823   \n",
+       "\n",
+       "                      Barcelona_temp  Bilbao_temp  Madrid_temp  \\\n",
+       "Madrid_wind_speed           0.080133     0.060467     0.109572   \n",
+       "Valencia_wind_deg          -0.113788    -0.099050    -0.166092   \n",
+       "Valencia_wind_speed        -0.021456    -0.022676    -0.011982   \n",
+       "Seville_humidity           -0.617797    -0.604733    -0.717171   \n",
+       "Madrid_humidity            -0.684867    -0.634825    -0.802605   \n",
+       "Bilbao_clouds_all          -0.023171    -0.114118    -0.046686   \n",
+       "Bilbao_wind_speed           0.018967     0.142435     0.031245   \n",
+       "Seville_clouds_all         -0.186463    -0.152393    -0.227094   \n",
+       "Barcelona_wind_speed        0.116240     0.120361     0.089365   \n",
+       "Madrid_clouds_all          -0.223940    -0.174079    -0.262908   \n",
+       "Seville_wind_speed          0.085395     0.082904     0.108460   \n",
+       "Seville_pressure            0.085439     0.072489     0.091776   \n",
+       "Bilbao_snow_3h             -0.086561    -0.096477    -0.081209   \n",
+       "Seville_rain_3h            -0.041804    -0.032691    -0.043338   \n",
+       "Barcelona_rain_3h          -0.042970    -0.043223    -0.039565   \n",
+       "Valencia_snow_3h           -0.029135    -0.031726    -0.023734   \n",
+       "Madrid_weather_id           0.085587     0.068572     0.136829   \n",
+       "Barcelona_weather_id        0.029239     0.053303     0.025671   \n",
+       "Seville_weather_id          0.168608     0.134535     0.185768   \n",
+       "Valencia_temp               0.914601     0.854892     0.915753   \n",
+       "Bilbao_weather_id           0.128188     0.190635     0.143126   \n",
+       "Seville_temp                0.852651     0.839014     0.917075   \n",
+       "Valencia_humidity          -0.247168    -0.260946    -0.261356   \n",
+       "Barcelona_temp              1.000000     0.865705     0.903143   \n",
+       "Bilbao_temp                 0.865705     1.000000     0.875271   \n",
+       "Madrid_temp                 0.903143     0.875271     1.000000   \n",
+       "load_shortfall_3h           0.182673     0.176411     0.186036   \n",
+       "month                       0.203184     0.239443     0.182860   \n",
+       "day                        -0.001659     0.020639     0.000861   \n",
+       "\n",
+       "                      load_shortfall_3h     month       day  \n",
+       "Madrid_wind_speed             -0.150981 -0.237445 -0.029954  \n",
+       "Valencia_wind_deg             -0.110849 -0.087571 -0.025467  \n",
+       "Valencia_wind_speed           -0.142791 -0.237156 -0.000340  \n",
+       "Seville_humidity              -0.167290 -0.111622  0.032979  \n",
+       "Madrid_humidity               -0.150536 -0.076567  0.047372  \n",
+       "Bilbao_clouds_all             -0.127293 -0.117452  0.025688  \n",
+       "Bilbao_wind_speed             -0.081602 -0.086698 -0.008020  \n",
+       "Seville_clouds_all            -0.091804 -0.170345  0.010582  \n",
+       "Barcelona_wind_speed          -0.103633 -0.122221 -0.009699  \n",
+       "Madrid_clouds_all             -0.081623 -0.118792  0.035940  \n",
+       "Seville_wind_speed            -0.048433 -0.122624 -0.030206  \n",
+       "Seville_pressure               0.037904  0.013314  0.030015  \n",
+       "Bilbao_snow_3h                -0.031721 -0.075644 -0.055138  \n",
+       "Seville_rain_3h               -0.032945 -0.055265  0.004448  \n",
+       "Barcelona_rain_3h             -0.024720 -0.056726 -0.021814  \n",
+       "Valencia_snow_3h              -0.021633 -0.022720 -0.023046  \n",
+       "Madrid_weather_id              0.030868  0.068856 -0.031751  \n",
+       "Barcelona_weather_id           0.063868  0.025352 -0.035885  \n",
+       "Seville_weather_id             0.061104  0.100786  0.000676  \n",
+       "Valencia_temp                  0.173225  0.216464 -0.000728  \n",
+       "Bilbao_weather_id              0.145875  0.141738 -0.017562  \n",
+       "Seville_temp                   0.159343  0.213623 -0.017066  \n",
+       "Valencia_humidity              0.043140  0.162713  0.047823  \n",
+       "Barcelona_temp                 0.182673  0.203184 -0.001659  \n",
+       "Bilbao_temp                    0.176411  0.239443  0.020639  \n",
+       "Madrid_temp                    0.186036  0.182860  0.000861  \n",
+       "load_shortfall_3h              1.000000  0.199048  0.092116  \n",
+       "month                          0.199048  1.000000  0.008826  \n",
+       "day                            0.092116  0.008826  1.000000  "
+      ]
+     },
+     "execution_count": 117,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_1.corr()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "id": "a906a889",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# selecting the correct columns and in the correct order\n",
+    "\n",
+    "\n",
+    "column_ = [col for col in df_1.columns if col == 'day' or col == 'time' or col == 'month'] \n",
+    "\n",
+    "others = [item for item in df_1.columns if 'wind'  in item  or  'pressure' in item \n",
+    "                      or 'cloud' in item or 'humidity' in item or 'Seville_weather' in item or 'Madrid_temp' in item] \n",
+    "\n",
+    "last_col = ['load_shortfall_3h']\n",
+    "\n",
+    "column_titles = column_ + others + last_col\n",
+    "\n",
+    "\n",
+    "column = column_ + others"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 119,
+   "id": "7a02968f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_1 = df_1.reindex(columns = column_titles)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 120,
+   "id": "ae05e46e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_1['time'] = df_1['time'].astype('category')\n",
+    "\n",
+    "df_1['time'] = df_1['time'].cat.codes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 121,
+   "id": "803b2b39",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 8763 entries, 0 to 8762\n",
+      "Data columns (total 19 columns):\n",
+      " #   Column                Non-Null Count  Dtype  \n",
+      "---  ------                --------------  -----  \n",
+      " 0   time                  8763 non-null   int8   \n",
+      " 1   month                 8763 non-null   int64  \n",
+      " 2   day                   8763 non-null   int64  \n",
+      " 3   Madrid_wind_speed     8763 non-null   float64\n",
+      " 4   Valencia_wind_deg     8763 non-null   int8   \n",
+      " 5   Valencia_wind_speed   8763 non-null   float64\n",
+      " 6   Seville_humidity      8763 non-null   float64\n",
+      " 7   Madrid_humidity       8763 non-null   float64\n",
+      " 8   Bilbao_clouds_all     8763 non-null   float64\n",
+      " 9   Bilbao_wind_speed     8763 non-null   float64\n",
+      " 10  Seville_clouds_all    8763 non-null   float64\n",
+      " 11  Barcelona_wind_speed  8763 non-null   float64\n",
+      " 12  Madrid_clouds_all     8763 non-null   float64\n",
+      " 13  Seville_wind_speed    8763 non-null   float64\n",
+      " 14  Seville_pressure      8763 non-null   int8   \n",
+      " 15  Seville_weather_id    8763 non-null   float64\n",
+      " 16  Valencia_humidity     8763 non-null   float64\n",
+      " 17  Madrid_temp           8763 non-null   float64\n",
+      " 18  load_shortfall_3h     8763 non-null   float64\n",
+      "dtypes: float64(14), int64(2), int8(3)\n",
+      "memory usage: 1.1 MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "#It can be observed from the data below that all the non of the 40 columns have null values \n",
+    "#and they now all have numeric values \n",
+    "\n",
+    "df_1.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0f69113",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 122,
+   "id": "57c1748b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "time                    -1.237868\n",
+       "month                   -1.207760\n",
+       "day                     -1.193873\n",
+       "Madrid_wind_speed        2.036462\n",
+       "Valencia_wind_deg       -1.192548\n",
+       "Valencia_wind_speed     35.645426\n",
+       "Seville_humidity        -1.017983\n",
+       "Madrid_humidity         -1.167537\n",
+       "Bilbao_clouds_all       -1.533417\n",
+       "Bilbao_wind_speed        3.631565\n",
+       "Seville_clouds_all       2.155921\n",
+       "Barcelona_wind_speed     1.493635\n",
+       "Madrid_clouds_all        0.142079\n",
+       "Seville_wind_speed       1.398580\n",
+       "Seville_pressure        -1.155787\n",
+       "Seville_weather_id      10.710308\n",
+       "Valencia_humidity       -0.734345\n",
+       "Madrid_temp             -0.612299\n",
+       "load_shortfall_3h       -0.118999\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 122,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#Majority of the factors contains less outliers in the data \n",
+    "#kurtosis is <3\n",
+    "\n",
+    "df_1.kurtosis()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a54318a6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8167954c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 123,
+   "id": "37ef7ebc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df_1.copy()\n",
+    "\n",
+    "X = df.drop(['load_shortfall_3h','time'], axis = 1)\n",
+    "\n",
+    "y = df['load_shortfall_3h']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaa0c480",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 124,
+   "id": "aec8e2f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_test = test_df[column]\n",
+    "X_t = X_test.drop('time',axis = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 125,
+   "id": "05c62bde",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "scaler = StandardScaler()\n",
+    "X_scaled = scaler.fit_transform(X)\n",
+    "X_t_Scaled = scaler.fit_transform(X_t)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 126,
+   "id": "475d4509",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Train-test split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X_scaled,\n",
+    "                                                    y,\n",
+    "                                                    test_size = 0.20,\n",
+    "                                                    random_state = 42,\n",
+    "                                                    shuffle = True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1445813f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 127,
+   "id": "acc3c1c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "LinearRegression()"
+      ]
+     },
+     "execution_count": 127,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "lm = LinearRegression()\n",
+    "    \n",
+    "lm.fit(X_train,y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 128,
+   "id": "97317ae8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LR RMSE: 5011.083643429062\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_hat = lm.predict(X_test)\n",
+    "print('LR RMSE:', np.sqrt(mean_squared_error(y_test, y_hat)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 129,
+   "id": "f9bd5589",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lm_y = lm.predict(X_t_Scaled)\n",
+    "\n",
+    "pre_dict = {'time':df_test[df_test.columns[0]],'load_shortfall_3h': lm_y} # dictionary containing predicted values\n",
+    "\n",
+    "predict_ed = pd.DataFrame(pre_dict) # dataframe with the date and load_shortfall_3h\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 130,
+   "id": "7552c4f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predict_ed.to_csv('Team.csv',index = False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4202225",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 131,
+   "id": "ce71be79",
+   "metadata": {},
+   "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>time</th>\n",
+       "      <th>load_shortfall_3h</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2018-01-01 00:00:00</td>\n",
+       "      <td>6302.579483</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2018-01-01 03:00:00</td>\n",
+       "      <td>6335.397607</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2018-01-01 06:00:00</td>\n",
+       "      <td>6909.880355</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2018-01-01 09:00:00</td>\n",
+       "      <td>6649.802924</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2018-01-01 12:00:00</td>\n",
+       "      <td>6548.866739</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  time  load_shortfall_3h\n",
+       "0  2018-01-01 00:00:00        6302.579483\n",
+       "1  2018-01-01 03:00:00        6335.397607\n",
+       "2  2018-01-01 06:00:00        6909.880355\n",
+       "3  2018-01-01 09:00:00        6649.802924\n",
+       "4  2018-01-01 12:00:00        6548.866739"
+      ]
+     },
+     "execution_count": 131,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b666a4fd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfce436b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From 88f6b5e6684f3443b4906449fb60e08eabb8defc Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <90265907+kwanda2426@users.noreply.github.com>
Date: Thu, 4 Nov 2021 16:17:32 +0200
Subject: [PATCH 3/6] trained model file

---
 assets/trained-models/mlr_model.pkl | Bin 0 -> 720 bytes
 1 file changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 assets/trained-models/mlr_model.pkl

diff --git a/assets/trained-models/mlr_model.pkl b/assets/trained-models/mlr_model.pkl
new file mode 100644
index 0000000000000000000000000000000000000000..28b6b1360588cc2de7557c127d39173fedeac49b
GIT binary patch
literal 720
zcmZo*nR=9o0StPiinDW46N~cnax(LPbbM}pN@|W?d{Sa@>XaS<AFyChYI;#>adBpT
z-jvBxG#jVXPSNP$P0K8a&&(@HElN%;D4EjH!<m;~l$)57S(Q4avxhA?zo0Tc0w~Ou
z7oU}%R6ND6hod0BII|?P3?$E&7oV1zSW*f!7HCNP6mP*E*5v%uwD>7KqIspc1(kZq
z`9-OExurQJnTbV3iIr1&c;bsvlk@Y6ONvU9OMvd^VFfFk(!-vY0#Pz~iZ?^+6lcby
zDeY5&rf7IGdJDEr$>8r{O)04?NCjzOO0$^K*#VJd?qRf<;^*h*^&bepgf~OUl%!7Q
zj#H=qW&AwS?6B#1ubGiXtpoR!Ew|OfYY%i@;h(hQXzBsUtxuoWU5GreaJk{tTeU3*
z4j;ZQ^hh}S!1l*6-d{{g4_uzndhcCv=z)ZF+phPY@o+fV?eARGR(`;>=uP*YOZg68
zqq?76oNsktM{x6}D-E^|lkc?dTWSz?;8JGi<e4TJ4jaRLW3AgO9i{-C)58h$c5!A(
zX=?G544xjg;^f4f#3G<yGNhe3q&FpRvR~%xG^Gvb-yYVY#Jp^9P;wS$=B1Yc)x}TA
z;L8vMg-V7na+pX1eK~tw<k>eXk{#YnH00b}pXAV8I_20Nt_X*4<Ibypwud@MJ%4Ps
z`CW*^SGM};Gv|glv~tx=U9~LO!7omF%6hk8hxl#$2^Xq@93Iu2Y~nl<=up<Jm8-Pd
z-=S~Kih?Lde+T7n87KE&@^iSm-cOr@-^)RV>xlHDGoB9LW7%g3{dID9H+4sdvXLFc
wmt63a1az_z$ZsM$(kqN^9C3j7O&}hcOykQ^i@*u7hs{9G$VAU@N@<cF0I1hJApigX

literal 0
HcmV?d00001


From 9a0838d45d666f8be077171cf71fde493c15c630 Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <90265907+kwanda2426@users.noreply.github.com>
Date: Thu, 4 Nov 2021 16:21:04 +0200
Subject: [PATCH 4/6] updated the directory for the pkl

---
 api.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/api.py b/api.py
index b438b2d..72f4d4c 100644
--- a/api.py
+++ b/api.py
@@ -30,7 +30,7 @@
 # Load our model into memory.
 # Please update this path to reflect your own trained model.
 static_model = load_model(
-    path_to_model='assets/trained-models/sendy_simple_lm_regression.pkl')
+    path_to_model='assets/trained-models/mlr_model.pkl')
 
 print ('-'*40)
 print ('Model succesfully loaded')

From ea18bee8716c4ae3af2179f9dd60ac029a13f29c Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <90265907+kwanda2426@users.noreply.github.com>
Date: Thu, 4 Nov 2021 16:22:42 +0200
Subject: [PATCH 5/6] updating the model directory

---
 api.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/api.py b/api.py
index 72f4d4c..f9711b6 100644
--- a/api.py
+++ b/api.py
@@ -1,8 +1,8 @@
 """
 
-    Simple Flask-based API for Serving an Sklearn Model.
+    Simple Flask-based API for Saving an Sklearn Model.
 
-    Author: Explore Data Science Academy.
+    Author: Kwanda Mazibuko
 
     Note:
     ---------------------------------------------------------------------

From bbf167f2e22db93501d539f0faba8b919d7de205 Mon Sep 17 00:00:00 2001
From: Kwanda Mazibuko <90265907+kwanda2426@users.noreply.github.com>
Date: Thu, 4 Nov 2021 18:53:06 +0200
Subject: [PATCH 6/6] Added my code for preprocessing

---
 model.py | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 59 insertions(+), 2 deletions(-)

diff --git a/model.py b/model.py
index f18e699..1e42f22 100644
--- a/model.py
+++ b/model.py
@@ -59,8 +59,65 @@ def _preprocess_data(data):
     # ---------------------------------------------------------------
 
     # ----------- Replace this code with your own preprocessing steps --------
-    predict_vector = feature_vector_df[['Pickup Lat','Pickup Long',
-                                        'Destination Lat','Destination Long']]
+    df_1 = feature_vector_df.copy() #creating a copy of data
+    
+    df_1['Valencia_pressure'].fillna(df_1['Valencia_pressure'].mean(), inplace=True) #imputing the null with the mean
+    df_1['time'] = pd.to_datetime(df_1['time']) # changing the date datatype
+
+
+    df_1.drop('Unnamed: 0',inplace = True,axis = 1) #deleting the first column
+    cols_to_drop = ['Bilbao_rain_1h','Bilbao_wind_deg','Barcelona_pressure','Barcelona_wind_deg',
+               'Barcelona_rain_1h','Seville_rain_1h','Bilbao_pressure','Madrid_pressure','Valencia_pressure'] #columns to drop
+
+    cols = [item for item in df_1.columns if 'max' in item or 'min' in item or '1h' in item] #selecting new columns
+
+    cols_to = cols_to_drop + cols #combining columns
+
+    df_1.drop(cols_to, inplace = True, axis = 1) #dropping unused columns
+
+    #Changing Dtypes of 'time' from object to 'datetime64'
+    
+    #Changing Dtypes of 'Valencia_wind_deg', 'Seville_pressure' from object to 'category'
+
+
+    cat_cols = [item for item in df_1.columns if 'pressure' in item or 'deg' in item]
+    
+    df_1[cat_cols] = df_1[cat_cols].astype('category')
+    
+    # Encoding 'Valencia_wind_deg', 'Seville_pressure' from 'category' to numeric values using 'cat.codes'
+
+    df_1['Valencia_wind_deg'] = df_1['Valencia_wind_deg'].cat.codes
+    
+    df_1['Seville_pressure'] = df_1['Seville_pressure'].cat.codes
+    
+    # extracing the date from date time
+    
+    df_1['month'] = df_1['time'].dt.month
+    
+    df_1['day'] = df_1['time'].dt.day
+    
+    df_1['time'] = df_1['time'].dt.time
+    
+    # selecting the correct columns and in the correct order
+    
+    column_ = [col for col in df_1.columns if col == 'day' or col == 'time' or col == 'month']
+    
+    others = [item for item in df_1.columns if 'wind'  in item  or  'pressure' in item 
+                      or 'cloud' in item or 'humidity' in item or 'Seville_weather' in item or 'Madrid_temp' in item]
+    
+    column = column_ + others # adding columns
+    
+    df_1 = df_1.reindex(columns = column_titles) # changing the index
+    
+    df_1['time'] = df_1['time'].astype('category') # changing time to category
+    
+    df_1['time'] = df_1['time'].cat.codes #changing time to encoding
+    
+    X_test = df_1[column]
+    
+    X_t = X_test.drop('time',axis = 1)
+    
+    predict_vector = X_t
     # ------------------------------------------------------------------------
 
     return predict_vector