gen_df_view.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## this NB generates `view_df` - a dataframe containing information from viewing runs\n",
    "- steps:\n",
    "- load `logfile_df` from psychopy logfile\n",
    "    - NB `logfile_df` has a row for each timestamps\n",
    "    - extract TR information and remove rows corresponding to timestamps before first TR\n",
    "- from `logfile_df`, extract `state_dict`: what events was visited on each wedding\n",
    "- from `logfile_df` and `state_dict`, make `timing_df` \n",
    "    - NB `timing_df` has a row for each event in the experiment\n",
    "- include wedding level information (schema and wed_id)\n",
    "- `timing_df` = `view_df`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import itertools\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import sklearn\n",
    "import brainiak\n",
    "import nilearn as nl\n",
    "from nilearn import image, plotting, input_data\n",
    "\n",
    "from glob import glob as glob\n",
    "\n",
    "from scipy.spatial import distance\n",
    "\n",
    "pd.options.display.max_rows = 200"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### load logfile_df and estimate the TR of each timestep\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_logfile(sub_num):\n",
    "  \"\"\" \n",
    "  read psychopy logifle into dataframe\n",
    "  \"\"\"\n",
    "  # initialize dataframe\n",
    "  df = pd.DataFrame(columns=['tstamp','logdata'])\n",
    "  df = df.astype({'tstamp':float})\n",
    "  # open logfile\n",
    "  fpath = 'data/behav/silvy_buckets/sub%iday2/%i_viewing.log'%(100+sub_num,sub_num)\n",
    "  f = open(fpath, \"r\")\n",
    "  # loop over logfile rows\n",
    "  for x in f:\n",
    "    # deal with S11,39\n",
    "    if len(x.split('\\t')) != 3: continue\n",
    "    tstamp,B,C = x.split('\\t')\n",
    "    tstamp = float(tstamp)\n",
    "    df.loc[tstamp,'logdata'] = C[:-1]\n",
    "    df.loc[tstamp,'tstamp'] = tstamp\n",
    "  return df\n",
    "\n",
    "def estimate_TR(df):\n",
    "  \"\"\"\n",
    "  takes logdf (indexed by tstamps)\n",
    "  includes the TR on each row\n",
    "  corrects for hemodynamic lag (HRF)\n",
    "  \"\"\"\n",
    "  TR_rate = 1.5\n",
    "  # first TR\n",
    "  first_TR_tstamp = df[df.logdata=='Keypress: equal'].iloc[0].tstamp\n",
    "  # center tstamps on first TR\n",
    "  df.tstamp = df.tstamp-first_TR_tstamp\n",
    "  # include TR column\n",
    "  df['TR'] = np.ceil(df.tstamp/TR_rate)\n",
    "  df = df.astype({'TR':int})\n",
    "  # remove negative TRs\n",
    "  df = df[df.TR>-1]\n",
    "  #  HRF hemodynamic lag \n",
    "  df.TR = df.TR + 3\n",
    "  # reindex by row number\n",
    "  df.index = np.arange(len(df))\n",
    "  return df\n",
    "\n",
    "def make_logfile_df(sub_num):\n",
    "  \"\"\"\n",
    "  wrapper for funs above\n",
    "  \"\"\"\n",
    "  df = read_logfile(sub_num)\n",
    "  df = estimate_TR(df)\n",
    "  return df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### go from logfile_df (indexed by timestamps) to timing_df (TR level information)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def init_sub_timing_df(logdf,sub_num):\n",
    "  \"\"\" \n",
    "  this fun transforms the logfile_df (each timestamp a row) \n",
    "  into the timing_df (each experiment event a row)\n",
    "  edit needed: \n",
    "    fun takes dict with info about the state_value\n",
    "  \"\"\"\n",
    "  vid_strL = ['vid1a','vid1b','vid2','vid3','vid4','vid5',\n",
    "           'vid1a_q','vid1b_q','vid2_q','vid3_q','vid4_q','vid5_q']\n",
    "  df_row_L = []\n",
    "  ## loop over video strings, extract onset TRs\n",
    "  for vid_str in vid_strL:\n",
    "    ## extract onset TR for wedding string\n",
    "    TR_vals = logdf[logdf.logdata == '%s: autoDraw = True'%vid_str].TR.values\n",
    "    if vid_str[-2:]=='_q':\n",
    "      df_row = pd.DataFrame.from_dict({\n",
    "        'sub_num':np.repeat(sub_num,2),\n",
    "        'vid_str':np.repeat(vid_str,2),\n",
    "        'wed_num':[0,11],\n",
    "        'onsetTR':TR_vals\n",
    "      })\n",
    "    else:\n",
    "      df_row = pd.DataFrame.from_dict({\n",
    "        'sub_num':np.repeat(sub_num,10),\n",
    "        'vid_str':np.repeat(vid_str,10),\n",
    "        'wed_num':np.arange(1,11),\n",
    "        'onsetTR':TR_vals\n",
    "      })\n",
    "    df_row_L.append(df_row)\n",
    "  df = pd.concat(df_row_L)\n",
    "  df.index = np.arange(len(df))\n",
    "  return df\n",
    "\n",
    "def include_offset_TRs(df):\n",
    "  \"\"\"\n",
    "  includes the offset TRs for each experimental event in a timing df\n",
    "  note from Silvy:\n",
    "    the first 26 seconds are intro, followed by 9 seconds start-event, \n",
    "    17 seconds campfire or flower (depending on label in pkl), \n",
    "    23 seconds coin or torch, 24 seconds egg or painting, and remainder gifts. \n",
    "    NB CURRENTLY USING 10S AS PLACEHOLDER FOR FINAL EVENT (gifts) \n",
    "  \"\"\"\n",
    "\n",
    "  ## dict with len of each vid\n",
    "  TR_rate = 1.5\n",
    "  vid_len_D = {'vid1a':26/TR_rate,'vid1b':9/TR_rate,'vid2':17/TR_rate,\n",
    "               'vid3':23/TR_rate,'vid4':24/TR_rate,'vid5':10/TR_rate,\n",
    "               'vid1a_q':26/TR_rate,'vid1b_q':9/TR_rate,'vid2_q':17/TR_rate,\n",
    "               'vid3_q':23/TR_rate,'vid4_q':24/TR_rate,'vid5_q':10/TR_rate\n",
    "              }\n",
    "  vid_len_D = {k:np.round(v).astype(int) for k,v in vid_len_D.items()}\n",
    "  for vid_str,num_TRs in vid_len_D.items():\n",
    "    df.loc[df['vid_str']==vid_str,'len_TRs'] = int(num_TRs)\n",
    "  df['offsetTR'] = df['onsetTR'] + df['len_TRs']\n",
    "  return df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### label each TR with state"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "def get_state_dict(logdf):\n",
    "  \"\"\"\n",
    "  returns a dict indexed by (wed_num,state_type/depth)\n",
    "  which gives the state_value [2a,2b,3a,3b,4a,4b]\n",
    "  \"\"\"\n",
    "  init_wed_idx_L = logdf[logdf.logdata.str[:len('Created vid1a_q')] == 'Created vid1a_q'].index\n",
    "  # from these rows, uncover what states were used for given wedding \n",
    "  state_dict = {}\n",
    "  for wed_num,init_wed_idx in enumerate(init_wed_idx_L):\n",
    "    for i,r in logdf.iloc[init_wed_idx:init_wed_idx+6].iterrows():\n",
    "      state_id = r.logdata.split(',')[5].split('/')[1].split('.')[1]\n",
    "      state_dict[(wed_num,int(state_id[0]))] = state_id\n",
    "  return state_dict\n",
    "\n",
    "def include_state_value(timing_df,state_dict):\n",
    "  \"\"\" \n",
    "  uses state_dict to include the column state_value in timing_df\n",
    "  \"\"\"\n",
    "  timing_df.loc[:,'state'] = 'N/A'\n",
    "  for i,r in timing_df.iterrows():\n",
    "    state_value = state_dict[(r.wed_num,int(r.vid_str[3]))]\n",
    "    timing_df.loc[i,'state'] = state_value\n",
    "  return timing_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### wedding level info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_wed_df(sub_num):\n",
    "  fpathL = glob('data/behav/silvy_buckets/sub%iday2/%i_viewing_*trials.csv'%(100+sub_num,sub_num))\n",
    "  fpathL.sort()\n",
    "  orderdf = pd.read_csv(fpathL[-1]).iloc[:12]\n",
    "  orderdf = orderdf.loc[:,('northOrSouth','stimFile1a')]\n",
    "  orderdf.columns = ['wed_schema','wed_id']\n",
    "  orderdf.wed_schema = orderdf.wed_schema.str.split('.').str[0].str[0].str.capitalize()\n",
    "  orderdf.wed_id = orderdf.wed_id.str.split('-').str[-1].str.split('.').str[0]\n",
    "  orderdf.loc[:,'wed_num'] = np.arange(12)\n",
    "  orderdf.loc[:,'sub_num'] = sub_num\n",
    "  return orderdf\n",
    "\n",
    "def include_wed_info(timing_df,wed_df):\n",
    "  for idx,wed_df_row in wed_df.iterrows():\n",
    "    sub_bool = timing_df.sub_num == wed_df_row.sub_num\n",
    "    wed_bool = timing_df.wed_num == wed_df_row.wed_num\n",
    "    timing_df.loc[sub_bool & wed_bool,'wed_id'] = wed_df_row.wed_id\n",
    "    timing_df.loc[sub_bool & wed_bool,'wed_schema'] = wed_df_row.wed_schema\n",
    "  return timing_df\n",
    "\n",
    "def include_path(view_df):\n",
    "  view_df.index = np.arange(len(view_df)) # ensure unique index per row\n",
    "  for idx,row in view_df.iterrows():\n",
    "    sub_bool = (row.sub_num == view_df.sub_num)\n",
    "    wed_bool = (row.wed_num == view_df.wed_num)\n",
    "    sub_wed_view_df = view_df[sub_bool & wed_bool]\n",
    "    path = sub_wed_view_df.wed_schema.iloc[0] + sub_wed_view_df[sub_wed_view_df.state.str[0] == '2'].state.str[1]\n",
    "    view_df.loc[idx,'path'] = path.values[0]\n",
    "  return view_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### wrapper for gathering all info of given subject"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_sub_view_df(sub_num):\n",
    "  \"\"\" \n",
    "  main wrapper function for loading info of a given subject\n",
    "  \"\"\"\n",
    "  log_df = make_logfile_df(sub_num)\n",
    "  wed_df = load_wed_df(sub_num)\n",
    "  state_dict = get_state_dict(log_df)\n",
    "  ## from logfile_df to timing_df\n",
    "  df = init_sub_timing_df(log_df,sub_num)\n",
    "  df = include_state_value(df,state_dict)\n",
    "  df = include_offset_TRs(df)\n",
    "  df = include_wed_info(df,wed_df)\n",
    "  df = include_path(df)\n",
    "  df = df.astype({'onsetTR':int,'len_TRs':int,'offsetTR':int})\n",
    "  df = df.sort_values('onsetTR')\n",
    "  return df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### MAIN: loop over subs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "err 0\n",
      "1\n",
      "err 1\n",
      "2\n",
      "err 2\n",
      "3\n",
      "4\n",
      "5\n",
      "6\n",
      "7\n",
      "8\n",
      "9\n",
      "10\n",
      "11\n",
      "12\n",
      "13\n",
      "14\n",
      "15\n",
      "16\n",
      "err 16\n",
      "17\n",
      "18\n",
      "19\n",
      "20\n",
      "err 20\n",
      "21\n",
      "err 21\n",
      "22\n",
      "23\n",
      "24\n",
      "25\n",
      "26\n",
      "27\n",
      "28\n",
      "29\n",
      "30\n",
      "31\n",
      "32\n",
      "33\n",
      "34\n",
      "35\n",
      "36\n",
      "37\n",
      "err 37\n",
      "38\n",
      "39\n",
      "err 39\n",
      "40\n",
      "41\n",
      "42\n",
      "43\n",
      "44\n"
     ]
    }
   ],
   "source": [
    "df_L = []\n",
    "for sub_num in np.arange(45):\n",
    "  print(sub_num)\n",
    "  try:\n",
    "    sub_view_df = load_sub_view_df(sub_num)\n",
    "    df_L.append(sub_view_df)\n",
    "  except:\n",
    "    print('err',sub_num)\n",
    "\n",
    "group_view_df = pd.concat(df_L)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>sub_num</th>\n",
       "      <th>vid_str</th>\n",
       "      <th>wed_num</th>\n",
       "      <th>onsetTR</th>\n",
       "      <th>state</th>\n",
       "      <th>len_TRs</th>\n",
       "      <th>offsetTR</th>\n",
       "      <th>wed_id</th>\n",
       "      <th>wed_schema</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>60</th>\n",
       "      <td>3</td>\n",
       "      <td>vid1a_q</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>1b</td>\n",
       "      <td>17</td>\n",
       "      <td>29</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>62</th>\n",
       "      <td>3</td>\n",
       "      <td>vid1b_q</td>\n",
       "      <td>0</td>\n",
       "      <td>29</td>\n",
       "      <td>1b</td>\n",
       "      <td>6</td>\n",
       "      <td>35</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>3</td>\n",
       "      <td>vid2_q</td>\n",
       "      <td>0</td>\n",
       "      <td>35</td>\n",
       "      <td>2b</td>\n",
       "      <td>11</td>\n",
       "      <td>46</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66</th>\n",
       "      <td>3</td>\n",
       "      <td>vid3_q</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>3a</td>\n",
       "      <td>15</td>\n",
       "      <td>64</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>3</td>\n",
       "      <td>vid4_q</td>\n",
       "      <td>0</td>\n",
       "      <td>67</td>\n",
       "      <td>4b</td>\n",
       "      <td>16</td>\n",
       "      <td>83</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>44</td>\n",
       "      <td>vid1b_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1091</td>\n",
       "      <td>1b</td>\n",
       "      <td>6</td>\n",
       "      <td>1097</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>44</td>\n",
       "      <td>vid2_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1097</td>\n",
       "      <td>2a</td>\n",
       "      <td>11</td>\n",
       "      <td>1108</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>67</th>\n",
       "      <td>44</td>\n",
       "      <td>vid3_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1111</td>\n",
       "      <td>3b</td>\n",
       "      <td>15</td>\n",
       "      <td>1126</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>44</td>\n",
       "      <td>vid4_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1129</td>\n",
       "      <td>4a</td>\n",
       "      <td>16</td>\n",
       "      <td>1145</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>44</td>\n",
       "      <td>vid5_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1145</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>1152</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2664 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    sub_num  vid_str  wed_num  onsetTR state  len_TRs  offsetTR wed_id  \\\n",
       "60        3  vid1a_q        0       12    1b       17        29     20   \n",
       "62        3  vid1b_q        0       29    1b        6        35     20   \n",
       "64        3   vid2_q        0       35    2b       11        46     20   \n",
       "66        3   vid3_q        0       49    3a       15        64     20   \n",
       "68        3   vid4_q        0       67    4b       16        83     20   \n",
       "..      ...      ...      ...      ...   ...      ...       ...    ...   \n",
       "63       44  vid1b_q       11     1091    1b        6      1097     38   \n",
       "65       44   vid2_q       11     1097    2a       11      1108     38   \n",
       "67       44   vid3_q       11     1111    3b       15      1126     38   \n",
       "69       44   vid4_q       11     1129    4a       16      1145     38   \n",
       "71       44   vid5_q       11     1145     5        7      1152     38   \n",
       "\n",
       "   wed_schema path  \n",
       "60          S   Sb  \n",
       "62          S   Sb  \n",
       "64          S   Sb  \n",
       "66          S   Sb  \n",
       "68          S   Sb  \n",
       "..        ...  ...  \n",
       "63          S   Sa  \n",
       "65          S   Sa  \n",
       "67          S   Sa  \n",
       "69          S   Sa  \n",
       "71          S   Sa  \n",
       "\n",
       "[2664 rows x 10 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "group_view_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# cleanup and save"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# sort and reindex\n",
    "group_view_df = group_view_df.sort_values(['sub_num','onsetTR'])\n",
    "group_view_df.index = np.arange(len(group_view_df))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>sub_num</th>\n",
       "      <th>vid_str</th>\n",
       "      <th>wed_num</th>\n",
       "      <th>onsetTR</th>\n",
       "      <th>state</th>\n",
       "      <th>len_TRs</th>\n",
       "      <th>offsetTR</th>\n",
       "      <th>wed_id</th>\n",
       "      <th>wed_schema</th>\n",
       "      <th>path</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>vid1a_q</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>1b</td>\n",
       "      <td>17</td>\n",
       "      <td>29</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>vid1b_q</td>\n",
       "      <td>0</td>\n",
       "      <td>29</td>\n",
       "      <td>1b</td>\n",
       "      <td>6</td>\n",
       "      <td>35</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>vid2_q</td>\n",
       "      <td>0</td>\n",
       "      <td>35</td>\n",
       "      <td>2b</td>\n",
       "      <td>11</td>\n",
       "      <td>46</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>vid3_q</td>\n",
       "      <td>0</td>\n",
       "      <td>49</td>\n",
       "      <td>3a</td>\n",
       "      <td>15</td>\n",
       "      <td>64</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>vid4_q</td>\n",
       "      <td>0</td>\n",
       "      <td>67</td>\n",
       "      <td>4b</td>\n",
       "      <td>16</td>\n",
       "      <td>83</td>\n",
       "      <td>20</td>\n",
       "      <td>S</td>\n",
       "      <td>Sb</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2659</th>\n",
       "      <td>44</td>\n",
       "      <td>vid1b_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1091</td>\n",
       "      <td>1b</td>\n",
       "      <td>6</td>\n",
       "      <td>1097</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2660</th>\n",
       "      <td>44</td>\n",
       "      <td>vid2_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1097</td>\n",
       "      <td>2a</td>\n",
       "      <td>11</td>\n",
       "      <td>1108</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2661</th>\n",
       "      <td>44</td>\n",
       "      <td>vid3_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1111</td>\n",
       "      <td>3b</td>\n",
       "      <td>15</td>\n",
       "      <td>1126</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2662</th>\n",
       "      <td>44</td>\n",
       "      <td>vid4_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1129</td>\n",
       "      <td>4a</td>\n",
       "      <td>16</td>\n",
       "      <td>1145</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2663</th>\n",
       "      <td>44</td>\n",
       "      <td>vid5_q</td>\n",
       "      <td>11</td>\n",
       "      <td>1145</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>1152</td>\n",
       "      <td>38</td>\n",
       "      <td>S</td>\n",
       "      <td>Sa</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2664 rows × 10 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      sub_num  vid_str  wed_num  onsetTR state  len_TRs  offsetTR wed_id  \\\n",
       "0           3  vid1a_q        0       12    1b       17        29     20   \n",
       "1           3  vid1b_q        0       29    1b        6        35     20   \n",
       "2           3   vid2_q        0       35    2b       11        46     20   \n",
       "3           3   vid3_q        0       49    3a       15        64     20   \n",
       "4           3   vid4_q        0       67    4b       16        83     20   \n",
       "...       ...      ...      ...      ...   ...      ...       ...    ...   \n",
       "2659       44  vid1b_q       11     1091    1b        6      1097     38   \n",
       "2660       44   vid2_q       11     1097    2a       11      1108     38   \n",
       "2661       44   vid3_q       11     1111    3b       15      1126     38   \n",
       "2662       44   vid4_q       11     1129    4a       16      1145     38   \n",
       "2663       44   vid5_q       11     1145     5        7      1152     38   \n",
       "\n",
       "     wed_schema path  \n",
       "0             S   Sb  \n",
       "1             S   Sb  \n",
       "2             S   Sb  \n",
       "3             S   Sb  \n",
       "4             S   Sb  \n",
       "...         ...  ...  \n",
       "2659          S   Sa  \n",
       "2660          S   Sa  \n",
       "2661          S   Sa  \n",
       "2662          S   Sa  \n",
       "2663          S   Sa  \n",
       "\n",
       "[2664 rows x 10 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "group_view_df.to_csv('deriv/view_df.csv')\n",
    "group_view_df"
   ]
  }
 ],
 "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": "3.6.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}