septum-mec/actions/calculate-statistics/data/10_calculate_spatial_statis...

483 lines
16 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"08:27:22 [I] klustakwik KlustaKwik2 version 0.2.6\n"
]
}
],
"source": [
"import os\n",
"import expipe\n",
"import pathlib\n",
"import numpy as np\n",
"import spatial_maps.stats as stats\n",
"import septum_mec.analysis.data_processing as dp\n",
"import head_direction.head as head\n",
"import spatial_maps as sp\n",
"import septum_mec.analysis.registration\n",
"import speed_cells.speed as spd\n",
"import septum_mec.analysis.spikes as spikes\n",
"import re\n",
"import joblib\n",
"import multiprocessing\n",
"import shutil\n",
"import psutil\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import septum_mec\n",
"import scipy.ndimage.measurements\n",
"from distutils.dir_util import copy_tree\n",
"\n",
"from tqdm import tqdm_notebook as tqdm\n",
"from tqdm._tqdm_notebook import tqdm_notebook\n",
"tqdm_notebook.pandas()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"max_speed = 1, # m/s only used for speed score\n",
"min_speed = 0.02, # m/s only used for speed score\n",
"position_sampling_rate = 100 # for interpolation\n",
"position_low_pass_frequency = 6 # for low pass filtering of position\n",
"\n",
"box_size = 1.0\n",
"bin_size = 0.02\n",
"smoothing_low = 0.03\n",
"smoothing_high = 0.06"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"project_path = dp.project_path()\n",
"\n",
"project = expipe.get_project(project_path)\n",
"actions = project.actions"
]
},
{
"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>action</th>\n",
" <th>channel_group</th>\n",
" <th>unit_name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1834-150319-3</td>\n",
" <td>0</td>\n",
" <td>71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1834-150319-3</td>\n",
" <td>0</td>\n",
" <td>75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1834-120319-4</td>\n",
" <td>0</td>\n",
" <td>85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1834-120319-1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1834-120319-2</td>\n",
" <td>0</td>\n",
" <td>39</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" action channel_group unit_name\n",
"0 1834-150319-3 0 71\n",
"1 1834-150319-3 0 75\n",
"2 1834-120319-4 0 85\n",
"3 1834-120319-1 0 1\n",
"4 1834-120319-2 0 39"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"identify_neurons = actions['identify-neurons']\n",
"units = pd.read_csv(identify_neurons.data_path('units'))\n",
"units.head()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"data_loader = dp.Data(\n",
" position_sampling_rate=position_sampling_rate, \n",
" position_low_pass_frequency=position_low_pass_frequency,\n",
" box_size=box_size, bin_size=bin_size\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"first_row = units[units['action'] == '1849-060319-3'].iloc[0]\n",
"#first_row = sessions.iloc[50]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"scrolled": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/mikkel/.virtualenvs/expipe/lib/python3.6/site-packages/elephant/statistics.py:835: UserWarning: Instantaneous firing rate approximation contains negative values, possibly caused due to machine precision errors.\n",
" warnings.warn(\"Instantaneous firing rate approximation contains \"\n"
]
},
{
"data": {
"text/plain": [
"average_rate 3.095328\n",
"speed_score -0.063922\n",
"out_field_mean_rate 1.837642\n",
"in_field_mean_rate 5.122323\n",
"max_field_mean_rate 8.882211\n",
"max_rate 23.006163\n",
"sparsity 0.468122\n",
"selectivity 7.306812\n",
"interspike_interval_cv 3.970863\n",
"burst_event_ratio 0.397921\n",
"bursty_spike_ratio 0.676486\n",
"gridness -0.459487\n",
"border_score 0.078474\n",
"information_rate 0.965845\n",
"head_mean_ang 5.788704\n",
"head_mean_vec_len 0.043321\n",
"spacing 0.624971\n",
"orientation 22.067900\n",
"dtype: float64"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def process(row):\n",
" action_id = row['action']\n",
" channel_id = row['channel_group']\n",
" unit_id = row['unit_name']\n",
" \n",
" # common values for all units == faster calculations\n",
" x, y, t, speed = map(data_loader.tracking(action_id).get, ['x', 'y', 't', 'v'])\n",
" ang, ang_t = map(data_loader.head_direction(action_id).get, ['a', 't'])\n",
" occupancy_map = data_loader.occupancy(action_id)\n",
" xbins, ybins = data_loader.spatial_bins\n",
" box_size_, bin_size_ = data_loader.box_size_, data_loader.bin_size_\n",
" prob_dist = data_loader.prob_dist(action_id)\n",
" \n",
" smooth_low_occupancy_map = sp.maps.smooth_map(occupancy_map, bin_size=bin_size_, smoothing=smoothing_low)\n",
" smooth_high_occupancy_map = sp.maps.smooth_map(occupancy_map, bin_size=bin_size_, smoothing=smoothing_high)\n",
" \n",
" spike_times = data_loader.spike_train(action_id, channel_id, unit_id)\n",
"\n",
" # common\n",
" spike_map = sp.maps._spike_map(x, y, t, spike_times, xbins, ybins)\n",
"\n",
" smooth_low_spike_map = sp.maps.smooth_map(spike_map, bin_size=bin_size_, smoothing=smoothing_low)\n",
" smooth_high_spike_map = sp.maps.smooth_map(spike_map, bin_size=bin_size_, smoothing=smoothing_high)\n",
"\n",
" smooth_low_rate_map = smooth_low_spike_map / smooth_low_occupancy_map\n",
" smooth_high_rate_map = smooth_high_spike_map / smooth_high_occupancy_map\n",
"\n",
" # find fields with laplace\n",
" fields_laplace = sp.separate_fields_by_laplace(smooth_high_rate_map)\n",
" fields = fields_laplace.copy() # to be cleaned by Ismakov\n",
" fields_areas = scipy.ndimage.measurements.sum(\n",
" np.ones_like(fields), fields, index=np.arange(fields.max() + 1))\n",
" fields_area = fields_areas[fields]\n",
" fields[fields_area < 9.0] = 0\n",
"\n",
" # find fields with Ismakov-method\n",
" fields_ismakov, radius = sp.separate_fields_by_distance(smooth_high_rate_map)\n",
" fields_ismakov_real = fields_ismakov * bin_size\n",
" approved_fields = []\n",
"\n",
" # remove fields not found by both methods\n",
" for point in fields_ismakov:\n",
" field_id = fields[tuple(point)]\n",
" approved_fields.append(field_id)\n",
"\n",
" for field_id in np.arange(1, fields.max() + 1):\n",
" if not field_id in approved_fields:\n",
" fields[fields == field_id] = 0\n",
"\n",
" # varying statistics\n",
" average_rate = len(spike_times) / (t.max() - t.min())\n",
"\n",
" max_rate = smooth_low_rate_map.max()\n",
"\n",
" out_field_mean_rate = smooth_low_rate_map[np.where(fields == 0)].mean()\n",
" in_field_mean_rate = smooth_low_rate_map[np.where(fields != 0)].mean()\n",
" max_field_mean_rate = smooth_low_rate_map[np.where(fields == 1)].mean()\n",
"\n",
" interspike_interval = np.diff(spike_times)\n",
" interspike_interval_cv = interspike_interval.std() / interspike_interval.mean()\n",
"\n",
" autocorrelogram = sp.autocorrelation(smooth_high_rate_map)\n",
" peaks = sp.fields.find_peaks(autocorrelogram)\n",
" real_peaks = peaks * bin_size\n",
" autocorrelogram_box_size = box_size * autocorrelogram.shape[0] / smooth_high_rate_map.shape[0]\n",
" spacing, orientation = sp.spacing_and_orientation(real_peaks, autocorrelogram_box_size)\n",
" orientation *= 180 / np.pi\n",
"\n",
" selectivity = stats.selectivity(smooth_low_rate_map, prob_dist)\n",
"\n",
" sparsity = stats.sparsity(smooth_low_rate_map, prob_dist)\n",
"\n",
" gridness = sp.gridness(smooth_high_rate_map)\n",
"\n",
" border_score = sp.border_score(smooth_high_rate_map, fields_laplace)\n",
"\n",
" information_rate = stats.information_rate(smooth_high_rate_map, prob_dist)\n",
"\n",
" single_spikes, bursts, bursty_spikes = spikes.find_bursts(spike_times, threshold=0.01)\n",
" burst_event_ratio = np.sum(bursts) / (np.sum(single_spikes) + np.sum(bursts))\n",
" bursty_spike_ratio = np.sum(bursty_spikes) / (np.sum(bursty_spikes) + np.sum(single_spikes))\n",
" mean_spikes_per_burst = np.sum(bursty_spikes) / np.sum(bursts)\n",
"\n",
" speed_score = spd.speed_correlation(\n",
" speed, t, spike_times, min_speed=min_speed, max_speed=max_speed)\n",
"\n",
" ang_bin, ang_rate = head.head_direction_rate(spike_times, ang, ang_t)\n",
"\n",
" head_mean_ang, head_mean_vec_len = head.head_direction_score(ang_bin, ang_rate)\n",
"\n",
" result = pd.Series({\n",
" 'average_rate': average_rate,\n",
" 'speed_score': speed_score,\n",
" 'out_field_mean_rate': out_field_mean_rate,\n",
" 'in_field_mean_rate': in_field_mean_rate,\n",
" 'max_field_mean_rate': max_field_mean_rate,\n",
" 'max_rate': max_rate,\n",
" 'sparsity': sparsity,\n",
" 'selectivity': selectivity,\n",
" 'interspike_interval_cv': float(interspike_interval_cv),\n",
" 'burst_event_ratio': burst_event_ratio,\n",
" 'bursty_spike_ratio': bursty_spike_ratio,\n",
" 'gridness': gridness,\n",
" 'border_score': border_score,\n",
" 'information_rate': information_rate,\n",
" 'head_mean_ang': head_mean_ang,\n",
" 'head_mean_vec_len': head_mean_vec_len,\n",
" 'spacing': spacing,\n",
" 'orientation': orientation\n",
" })\n",
" return result\n",
" \n",
"process(first_row)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "837fde7fe486422bac67341ff512a4e1",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=0, max=1281), HTML(value='')))"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/mikkel/apps/expipe-project/spatial-maps/spatial_maps/stats.py:13: RuntimeWarning: invalid value encountered in log2\n",
" return (np.nansum(np.ravel(tmp_rate_map * np.log2(tmp_rate_map/avg_rate) *\n",
"/home/mikkel/apps/expipe-project/spatial-maps/spatial_maps/stats.py:13: RuntimeWarning: divide by zero encountered in log2\n",
" return (np.nansum(np.ravel(tmp_rate_map * np.log2(tmp_rate_map/avg_rate) *\n",
"/home/mikkel/apps/expipe-project/spatial-maps/spatial_maps/stats.py:13: RuntimeWarning: invalid value encountered in multiply\n",
" return (np.nansum(np.ravel(tmp_rate_map * np.log2(tmp_rate_map/avg_rate) *\n",
"/home/mikkel/.virtualenvs/expipe/lib/python3.6/site-packages/ipykernel_launcher.py:56: RuntimeWarning: Mean of empty slice.\n",
"/home/mikkel/.virtualenvs/expipe/lib/python3.6/site-packages/numpy/core/_methods.py:85: RuntimeWarning: invalid value encountered in double_scalars\n",
" ret = ret.dtype.type(ret / rcount)\n",
"/home/mikkel/.virtualenvs/expipe/lib/python3.6/site-packages/ipykernel_launcher.py:57: RuntimeWarning: Mean of empty slice.\n",
"/home/mikkel/.virtualenvs/expipe/lib/python3.6/site-packages/ipykernel_launcher.py:82: RuntimeWarning: invalid value encountered in long_scalars\n"
]
}
],
"source": [
"results = units.merge(\n",
" units.progress_apply(process, axis=1), \n",
" left_index=True, right_index=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"output_path = pathlib.Path(\"output\") / \"calculate-statistics\"\n",
"output_path.mkdir(exist_ok=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"units.to_csv(output_path / \"units.csv\", index=False)\n",
"results.to_csv(output_path / \"results.csv\", index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Store results in Expipe action"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"statistics_action = project.require_action(\"calculate-statistics\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"statistics_action.data[\"units\"] = \"units.csv\"\n",
"statistics_action.data[\"results\"] = \"results.csv\"\n",
"copy_tree(output_path, str(statistics_action.data_path()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"septum_mec.analysis.registration.store_notebook(statistics_action, \"10_calculate_spatial_statistics.ipynb\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"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": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}