{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "class state_gen_old:\n",
    "    \"\"\"\"\"\"\n",
    "    def __init__(self,pattern_start,pattern_stop,null_state=\"Null\"):\n",
    "        self.previous = null_state\n",
    "        self.null_state=null_state\n",
    "        self.pattern_start=pattern_start\n",
    "        self.pattern_stop=pattern_stop\n",
    "        \n",
    "    def __call__(self,actual):\n",
    "        \n",
    "        if(not(pd.isnull(actual))):\n",
    "            \n",
    "            #Start condition\n",
    "            if((re.search(self.pattern_start,actual))!=None):\n",
    "                self.previous=actual\n",
    "                \n",
    "            #End Condition\n",
    "            elif((re.search(self.pattern_stop,actual))!=None):\n",
    "                self.previous = self.null_state\n",
    "            \n",
    "        return self.previous\n",
    "            \n",
    "            \n",
    "class state_gen_new:\n",
    "    \"\"\"\"\"\"\n",
    "    def __init__(self,pattern_start,pattern_stop,split = False,null_state=\"Null\"):\n",
    "        self.previous = null_state\n",
    "        self.null_state = null_state\n",
    "        self.pattern_start = pattern_start\n",
    "        self.pattern_stop = pattern_stop\n",
    "        self.split = split\n",
    "        \n",
    "    def process_state(self,state):\n",
    "        if (self.split):\n",
    "            #Keep the root of the state (eg. _Y6014 IntervalStart --> _Y6014)\n",
    "            state =  state.split()[0]\n",
    "        return state\n",
    "\n",
    "    def __call__(self,actual):\n",
    "        if(not(pd.isnull(actual))):\n",
    "            #Start condition\n",
    "            if((re.search(self.pattern_start,actual))!=None):\n",
    "                self.previous = self.process_state(actual)\n",
    "                            \n",
    "            #End Condition\n",
    "            elif((re.search(self.pattern_stop,actual))!=None):\n",
    "                self.previous = self.null_state\n",
    "                            \n",
    "        return self.previous"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "path_old= r\"C:\\Users\\jeuux\\Desktop\\Carrera\\MoAI\\TFM\\AnnotatedData\\Accelerometer_Data\\Participants\\0404b\\CompleteData\\segments_data.npy\"\n",
    "path_new = r\"C:\\Users\\jeuux\\Desktop\\Carrera\\MoAI\\TFM\\AnnotatedData\\FinalDatasets\\Participants\\0404b\\FullDataset\\segments_data.npy\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# # df_old = pd.read_csv(path_old)\n",
    "# df_old = pd.read_csv(path_new)\n",
    "# df_new = pd.read_csv(path_new)\n",
    "targets_old = np.load(path_old)\n",
    "targets_new = np.load(path_new)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "targets_old[0] == targets_new[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "targets_old == targets_new"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##get targets and valid intervals\n",
    "generator_target_old=state_gen_old(\"AG\",\"Behaviour End\")\n",
    "df_old[\"target\"]=df_old[\"Event\"].apply(lambda event: generator_target_old(event))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_old.target.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "##get targets and valid intervals\n",
    "generator_target_new=state_gen_new(\"AG\",\"Behaviour End\")\n",
    "df_new[\"target\"]=df_new[\"Event\"].apply(lambda event: generator_target_new(event))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_new.target.value_counts() ==df_old.target.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_new[df_new[\"Recording timestamp\"]==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df0_path = r\"C:\\Users\\jeuux\\Desktop\\Carrera\\MoAI\\TFM\\AnnotatedData\\Accelerometer_Data\\Participants\\0705b\\CompleteData\\CompleteData_raw_0705b.csv\"\n",
    "df1_path = r\"C:\\Users\\jeuux\\Desktop\\Carrera\\MoAI\\TFM\\AnnotatedData\\FinalDatasets\\Participants\\0705b\\FullDataset\\FullDataset_raw_0705b.csv\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df0 = pd.read_csv(df0_path)\n",
    "df1 = pd.read_csv(df1_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df0[df0[\"Recording timestamp\"]==0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df1[df1[\"Recording timestamp\"]==0]"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}