Logic for design matrix creation

notebooks/create_design_matrix.ipynb

@@ -0,0 +1,100 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Notebook to create and store a design matrix of behavior and spikes "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from spike_tools import (\n",
+    "    general as spike_general,\n",
+    "    analysis as spike_analysis,\n",
+    ")\n",
+    "import wcst_encode.data_utils as data_utils\n",
+    "from wcst_encode.constants import COLUMN_NAMES\n",
+    "\n",
+    "species = 'nhp'\n",
+    "subject = 'SA'\n",
+    "exp = 'WCST'\n",
+    "session = 20180802  # this is the session for which there are spikes at the moment. \n",
+    "\n",
+    "tau_pre = 20\n",
+    "tau_post = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "spikes_by_bins = pd.read_pickle('/data/processed/sub-SA_sess-20180802_spike_counts_binsize_50.pickle')\n",
+    "beh_by_bins = pd.read_pickle('/data/processed/sub-SA_sess-20180802_behavior_binsize_50.pickle')\n",
+    "intervals = pd.read_pickle(\"/data/processed/sub-SA_sess-20180802_interval_1500_fb_1500_binsize_50.pickle\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "column_names_w_units = COLUMN_NAMES + spikes_by_bins.columns[1:].tolist()\n",
+    "design_mat = data_utils.get_design_matrix(spikes_by_bins, beh_by_bins, column_names_w_units, tau_pre, tau_post)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "design_mat.to_pickle(\"/data/processed/sub-SA_sess-20180802_design_mat_taupre_20_taupost_0_binsize_50.pickle\")"
+   ]
+  }
+ ],
+ "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": "3.10.6"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/format_beh.ipynb

@@ -0,0 +1,105 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from spike_tools import (\n",
+    "    general as spike_general,\n",
+    "    analysis as spike_analysis,\n",
+    ")\n",
+    "import wcst_encode.data_utils\n",
+    "from wcst_encode.constants import FEATURES\n",
+    "\n",
+    "species = 'nhp'\n",
+    "subject = 'SA'\n",
+    "exp = 'WCST'\n",
+    "session = 20180802  # this is the session for which there are spikes at the moment. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "behavior_file = spike_general.get_behavior_path(subject, session)\n",
+    "behavior_data = pd.read_csv(\"/data/sub-SA_sess-20180802_object_features.csv\")\n",
+    "valid_beh = behavior_data[behavior_data.Response.isin([\"Correct\", \"Incorrect\"])]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "behavior_by_bins = data_utils.get_behavior_by_bins(50, valid_beh)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "behavior_by_bins.to_pickle('/data/processed/sub-SA_sess-20180802_behavior_binsize_50.pickle')"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Grab bin idxs of interval around fb onset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "intervals = data_utils.get_trial_intervals(valid_beh, pre_interval=1500, post_interval=1500, bin_size=50)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "intervals.to_pickle(\"/data/processed/sub-SA_sess-20180802_interval_1500_fb_1500_binsize_50.pickle\")"
+   ]
+  }
+ ],
+ "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": "3.10.6"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

wcst_encode/constants.py

@@ -0,0 +1,12 @@
+# useful constants during analysis
+
+FEATURES = [
+    'CIRCLE', 'SQUARE', 'STAR', 'TRIANGLE', 
+    'CYAN', 'GREEN', 'MAGENTA', 'YELLOW', 
+    'ESCHER', 'POLKADOT', 'RIPPLE', 'SWIRL'
+]
+
+NUM_UNITS = 59
+
+COLUMN_NAMES_W_UNITS = FEATURES + ["CORRECT", "INCORRECT"] + [f"unit_{i}" for i in range(0, NUM_UNITS)]
+COLUMN_NAMES = FEATURES + ["CORRECT", "INCORRECT"]