diff --git a/weather_analysis.ipynb b/weather_analysis.ipynb
new file mode 100644
index 0000000..81bf244
--- /dev/null
+++ b/weather_analysis.ipynb
@@ -0,0 +1,431 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib\n",
+    "import seaborn as sns\n",
+    "from pylab import rcParams\n",
+    "import os\n",
+    "import gzip\n",
+    "from tqdm import tqdm\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "%matplotlib inline\n",
+    "%config InlineBackend.figure_format='retina'\n",
+    "\n",
+    "sns.set(style='whitegrid', palette='muted', font_scale=1.2)\n",
+    "\n",
+    "HAPPY_COLORS_PALETTE = [\"#01BEFE\", \"#FFDD00\", \"#FF7D00\", \"#FF006D\", \"#ADFF02\", \"#8F00FF\"]\n",
+    "\n",
+    "sns.set_palette(sns.color_palette(HAPPY_COLORS_PALETTE))\n",
+    "rcParams['figure.figsize'] = 20, 10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "full_df = pd.read_csv('full_df.csv')\n",
+    "\n",
+    "full_df = full_df[full_df['IndoorProb']!=100]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>Unnamed: 0</th>\n",
+       "      <th>Patient</th>\n",
+       "      <th>Cohort</th>\n",
+       "      <th>Day</th>\n",
+       "      <th>StepPerSec</th>\n",
+       "      <th>Timestamp</th>\n",
+       "      <th>IndoorProb</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>29017</th>\n",
+       "      <td>29017</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>HA</td>\n",
+       "      <td>Day1</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>1597302217</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29018</th>\n",
+       "      <td>29018</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>HA</td>\n",
+       "      <td>Day1</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>1597302218</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29019</th>\n",
+       "      <td>29019</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>HA</td>\n",
+       "      <td>Day1</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>1597302219</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29020</th>\n",
+       "      <td>29020</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>HA</td>\n",
+       "      <td>Day1</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>1597302220</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29021</th>\n",
+       "      <td>29021</td>\n",
+       "      <td>1000</td>\n",
+       "      <td>HA</td>\n",
+       "      <td>Day1</td>\n",
+       "      <td>0.875</td>\n",
+       "      <td>1597302221</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Unnamed: 0  Patient Cohort   Day  StepPerSec   Timestamp  IndoorProb\n",
+       "29017       29017     1000     HA  Day1       0.875  1597302217           0\n",
+       "29018       29018     1000     HA  Day1       0.875  1597302218           0\n",
+       "29019       29019     1000     HA  Day1       0.875  1597302219           0\n",
+       "29020       29020     1000     HA  Day1       0.875  1597302220           0\n",
+       "29021       29021     1000     HA  Day1       0.875  1597302221           0"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "full_df.reset_index(inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1000, 1001, 1002, 1003, 1004, 1005, 1006, 1007, 1008, 1009, 1010,\n",
+       "       1011, 1012, 1013, 1014, 1015, 1016, 1017, 1018, 1019, 1020, 1021,\n",
+       "       1022, 1023, 1024, 1025, 1026, 1027, 1028, 1029, 2000, 2001, 2002,\n",
+       "       2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013,\n",
+       "       3000, 3001, 3002, 3003, 3004, 3005, 3006, 3007, 3008, 3009, 3010,\n",
+       "       3011, 3013, 3014, 4002, 4005, 4011, 4013, 4019, 5000, 5003, 5005,\n",
+       "       5008, 5009, 5010, 5012, 5019], dtype=int64)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_df['Patient'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "71"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(full_df['Patient'].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<AxesSubplot:>"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1440x720 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "image/png": {
+       "height": 579,
+       "width": 1177
+      }
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "full_df[full_df['Patient']==1000].StepPerSec.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#walking.StepPerSec.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 93,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extracting_daily_weather(folder, sort=False):\n",
+    "    daily_stats = []\n",
+    "    non_valid_stats = []\n",
+    "    num_days = list(range(1,8))\n",
+    "    for f in os.listdir(folder):\n",
+    "        if f.startswith('weather') and f.endswith('.json'):\n",
+    "            w_file = pd.read_json(os.path.join(folder, f))\n",
+    "            day = f.split('-')[3]\n",
+    "            num_days.remove(int(day[-1]))\n",
+    "            daily_stats.append((day,\n",
+    "                w_file['data'][0]['temp'],\n",
+    "                w_file['data'][0]['wind_speed']))\n",
+    "            #format: day, temp, wind speed, wind dir, precip, snow\n",
+    "    if num_days:\n",
+    "        for d in num_days:\n",
+    "            non_valid_stats.append((f'Day{d}', 'NaN', 'NaN'))\n",
+    "    if sort:\n",
+    "        return sorted(daily_stats, key=lambda x: x[1], reverse=True)\n",
+    "    return daily_stats+non_valid_stats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 94,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def daily_stats(df, feat, day=None):\n",
+    "    if day is None:\n",
+    "        return np.array([\n",
+    "            [np.mean(df[feat])],\n",
+    "            [np.median(df[feat])],\n",
+    "            [np.std(df[feat])],\n",
+    "            [np.max(df[feat])],\n",
+    "            [np.min(df[feat])]\n",
+    "        ])\n",
+    "    else:\n",
+    "        d_df = df[df['Day']==day]\n",
+    "        return np.array([\n",
+    "            [np.mean(d_df[feat])],\n",
+    "            [np.median(d_df[feat])],\n",
+    "            [np.std(d_df[feat])],\n",
+    "            [np.max(d_df[feat])],\n",
+    "            [np.min(d_df[feat])]\n",
+    "        ])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_full_df(folder, df, id):\n",
+    "    step_level = ['StepPerSec', 'StepPerMin']\n",
+    "    stats = ['mean', 'median', 'std', 'max', 'min']\n",
+    "\n",
+    "    stats_overall = pd.concat([pd.DataFrame(np.swapaxes(daily_stats(df, s), 0,1), columns=[f'{s}_{i}' for i in stats]) for s in step_level], axis=1)\n",
+    "    stats_daily = pd.concat([pd.DataFrame(np.swapaxes(daily_stats(df, s, f'Day{j}'), 0,1), columns=[f'Day{j}_{s}_{i}' for i in stats]) for j in range(1,8) for s in step_level], axis=1)\n",
+    "\n",
+    "    ds = extracting_daily_weather(folder)\n",
+    "    from_hot_to_cold = extracting_daily_weather(folder, sort=True)\n",
+    "\n",
+    "    weather_stats = pd.DataFrame(np.swapaxes(np.array([\n",
+    "        [from_hot_to_cold[0][0]], [from_hot_to_cold[0][1]], [from_hot_to_cold[-1][0]], [from_hot_to_cold[-1][1]]] + [[ds[i][2]] for i in range(7)]), 0,1), \n",
+    "        columns=['hottest_day', 'hottest_temp', 'coldest_day', 'coldest_temp']+[f'Day{i}_wind_speed' for i in range(1,8)])\n",
+    "\n",
+    "    final_weath_df = pd.concat([pd.DataFrame([sum(df['StepPerSec'].values)], columns=['NumOfSteps']), pd.DataFrame([id], columns=['ID']), stats_overall, weather_stats, stats_daily], axis=1)\n",
+    "\n",
+    "    return final_weath_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df = pd.DataFrame()\n",
+    "for el in full_df['Patient'].unique():\n",
+    "    p_df = full_df[full_df['Patient']==el]\n",
+    "    p_df['series_id'] = np.arange(len(p_df)) // 10 + 1\n",
+    "\n",
+    "    valid_idx = []\n",
+    "    for _,group in tqdm(p_df[p_df['StepPerSec'] > 0].groupby(['series_id', 'Patient']), position=0, leave=True):\n",
+    "        valid_idx+=group.index.values.tolist()\n",
+    "\n",
+    "    #valid_idx\n",
+    "    walking = p_df.loc[valid_idx]\n",
+    "    walking.reset_index(inplace=True)\n",
+    "    walking['StepPerMin'] = [el*60 for el in walking['StepPerSec'].values]\n",
+    "    \n",
+    "    folder = f'mobilised-contextual-factors-v1/{el}'\n",
+    "    \n",
+    "    s_df = create_full_df(folder, walking, el)\n",
+    "    final_df = pd.concat([final_df, s_df])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df.to_csv('weather_id_00thresh.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df = pd.DataFrame()\n",
+    "for el in full_df['Patient'].unique():\n",
+    "    p_df = full_df[full_df['Patient']==el]\n",
+    "    p_df['series_id'] = np.arange(len(p_df)) // 10 + 1\n",
+    "\n",
+    "    valid_idx = []\n",
+    "    for _,group in tqdm(p_df[p_df['StepPerSec'] > 0.5].groupby(['series_id', 'Patient']), position=0, leave=True):\n",
+    "        valid_idx+=group.index.values.tolist()\n",
+    "\n",
+    "    #valid_idx\n",
+    "    walking = p_df.loc[valid_idx]\n",
+    "    walking.reset_index(inplace=True)\n",
+    "    walking['StepPerMin'] = [el*60 for el in walking['StepPerSec'].values]\n",
+    "    \n",
+    "    folder = f'mobilised-contextual-factors-v1/{el}'\n",
+    "    \n",
+    "    s_df = create_full_df(folder, walking, el)\n",
+    "    final_df = pd.concat([final_df, s_df])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 119,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "final_df.to_csv('weather_id_05thresh.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.8.10 64-bit (microsoft store)",
+   "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": "3.8.10"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "df657c42ffabd81f9be5aedeaf438ee88f88a1b63551a526ed49ba8a75d7a743"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}