WIP - adding more examples & configuring to work with repo2docker, binder

.gitignore

@@ -1,3 +1,6 @@
 *.json
 *.nwb
 *-checkpoint.ipynb
+.local/
+.ipython/
+.jupyter/

README.md

@@ -1 +1,46 @@
-Example tutorials that we have developed for trainings and courses.
+# Brain Observatory Examples
+Example Jupyter notebooks for the Allen Brain Observatory
+
+This repository contains 3 sets of notebooks:
+
+- `tutorial` contains a set of notebooks that provide a self-guided tour of
+  accessing the Brain Observatory through the AllenSDK. It is expected that
+  users will explore these notebooks in order.
+- `workshops` contains notebooks used for any technical workshops that are run
+  by the Allen Institute. These are a snapshot and record of
+- `gallery` contains example notebooks that demonstrate some analysis or
+  visualization using the Brain Observatory and AllenSDK. These notebooks are
+  standalone entities. If it doesn't belong in the main tutorial and it is not
+  from a technical workshop, it probably goes here.
+
+```
+brain_observatory_gallery
+├─ tutorial/                  # Official tutorial for the Allen Brain Observatory
+│  ├─ requirements.txt        # packages required to run the tutorial    
+│  ├─ runtime.txt             # Python version required to run the tutorial
+│  ├─ Index.ipynb    
+│  ├─ 1. Intro to Brain Observatory.ipynb                              
+│  └─ ...      
+├─ gallery/                   # analysis files per experiment session
+│  ├─ requirements.txt        # packages required to run the tutorial    
+│  ├─ runtime.txt              
+│  ├─ joy_plots.ipynb           
+│  └─ ...                 
+└─ workshops/                 # technical workshops
+   ├─ 2018 Workshop Example/  # Example workshop
+   │  ├─ requirements.txt         
+   │  ├─ runtime.txt           
+   │  ├─ 1. Intro to Brain Observatory.ipynb                              
+   │  └─ ...      
+   ├─ 2018 Other Example/
+   └─ ...              
+```              
+
+
+## Running the examples
+
+Each folder contains the necessary assets to build a Docker container for the notebooks contained therein using repo2docker...
+
+1. install Docker
+2. install repo2docker: `pip install repo2docker` (you may want to install from source)
+3. build a docker container & launch a notebook server: `repo2docker ./`

binder/requirements.txt

@@ -0,0 +1,2 @@
+-r ../gallery/requirements.txt
+-r ../tutorial/requirements.txt

binder/runtime.txt

@@ -0,0 +1 @@
+python-2.7

binder/start

@@ -0,0 +1,5 @@
+#!/bin/bash
+export BRAIN_OBSERVATORY_MANIFEST=~/brain_observatory_data/manifest.json
+
+exec "$@"
+

gallery/decoding_from_sweep_response.ipynb

@@ -0,0 +1,224 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## requirements\n",
+    "# allensdk\n",
+    "# scikit-learn > 0.19\n",
+    "# xarray"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/local1/miniconda2/envs/jk/lib/python2.7/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.\n",
+      "  from ._conv import register_converters as _register_converters\n"
+     ]
+    }
+   ],
+   "source": [
+    "from allensdk.core.brain_observatory_cache import BrainObservatoryCache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "boc = BrainObservatoryCache(manifest_file='/local1/data/boc/manifest.json',)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "oeid = 541206592\n",
+    "\n",
+    "# Initializations:\n",
+    "nwb_dataset = boc.get_ophys_experiment_data(oeid)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import xarray as xr\n",
+    "\n",
+    "from allensdk.brain_observatory.natural_scenes import NaturalScenes\n",
+    "\n",
+    "def get_ns_msr(nwb_dataset):\n",
+    "    ns = NaturalScenes(nwb_dataset)\n",
+    "    mean_sweep_response = ns.mean_sweep_response.copy()\n",
+    "    \n",
+    "    # I don't know what dx is. goodbye!\n",
+    "    mean_sweep_response.drop('dx',axis=1,inplace=True)\n",
+    "    \n",
+    "    # annotate the dataframe with useful indices and columns\n",
+    "    time = pd.Series(\n",
+    "        ns.timestamps[ns.stim_table['start']],\n",
+    "        name='time',\n",
+    "    )\n",
+    "    neurons = pd.Series(\n",
+    "        ns.cell_id,\n",
+    "        name='neuron',\n",
+    "    )\n",
+    "    mean_sweep_response.set_index(time,inplace=True)\n",
+    "    mean_sweep_response.columns = neurons\n",
+    "    \n",
+    "    images = ns.stim_table\n",
+    "    \n",
+    "    return images, mean_sweep_response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   frame  start    end\n",
+      "0     92  16125  16132\n",
+      "1     27  16133  16140\n",
+      "2     52  16140  16147\n",
+      "3     37  16148  16155\n",
+      "4    103  16155  16162\n",
+      "neuron     541510267  541510270  541510307  541510405  588381938  541510410  \\\n",
+      "time                                                                          \n",
+      "545.19658   2.750398   3.113332   3.283231   1.035660   2.312769   1.005320   \n",
+      "545.46195   5.472741   4.520462   1.848134   1.509070   3.900594   2.375818   \n",
+      "545.69416   4.938696   1.872071   0.822514  -0.366550   0.590227   0.577107   \n",
+      "545.95953   0.686303  -1.502568  -2.128904  -0.779033  -3.098761   0.632175   \n",
+      "546.19174  -2.763241  -2.317277  -1.518564  -1.131271  -3.716857   0.189942   \n",
+      "\n",
+      "neuron     541511183  541510394  588381886  541511196    ...      588381999  \\\n",
+      "time                                                     ...                  \n",
+      "545.19658   1.795959   1.302906   1.109441   2.644591    ...       3.245388   \n",
+      "545.46195   0.627758   0.452645  -1.946570  -0.088816    ...       5.051270   \n",
+      "545.69416  -0.431362   3.239566  -2.953792   0.519713    ...       0.117338   \n",
+      "545.95953   2.272473   4.147108  -4.235024  -0.116484    ...      -3.436971   \n",
+      "546.19174   1.049816   0.004382  -3.942320  -2.070535    ...      -3.320092   \n",
+      "\n",
+      "neuron     541510679  541509977  541510142  541509981  541509952  541510950  \\\n",
+      "time                                                                          \n",
+      "545.19658   1.204343   3.223873  -0.614828   1.594057   2.538169   9.322724   \n",
+      "545.46195   3.157544   2.147983   3.462305   1.155841   3.599893  10.790494   \n",
+      "545.69416   2.204452   0.433436   1.692538   4.946897  -2.181524   1.229501   \n",
+      "545.95953   1.661621  -1.256703   0.234285   5.248888  -1.481765  -3.012385   \n",
+      "546.19174   0.768980   0.713630   4.319497   1.107409   0.044746  -4.763652   \n",
+      "\n",
+      "neuron     541511172  541509957  541511118  \n",
+      "time                                        \n",
+      "545.19658   3.246232  17.838305  44.883263  \n",
+      "545.46195   3.700325  41.864319  55.052734  \n",
+      "545.69416   1.446858  19.081219  -0.731454  \n",
+      "545.95953   0.283391  -6.771274 -18.988461  \n",
+      "546.19174  -0.807627 -15.687251 -24.453199  \n",
+      "\n",
+      "[5 rows x 154 columns]\n"
+     ]
+    }
+   ],
+   "source": [
+    "y, X = get_ns_msr(nwb_dataset)\n",
+    "print y.head()\n",
+    "print X.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "def decode(msrx):\n",
+    "    \n",
+    "    # get features and output\n",
+    "    X = msrx.data\n",
+    "    y = msrx['natural_image']\n",
+    "    \n",
+    "    # split training & testing\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,stratify=y)\n",
+    "    \n",
+    "    # do the classification\n",
+    "    lm = LogisticRegression(\n",
+    "        solver='saga',\n",
+    "        multi_class='ovr',\n",
+    "        penalty='l1',\n",
+    "        n_jobs=-1,\n",
+    "    )\n",
+    "    lm.fit(X_train,y_train)\n",
+    "    return lm.score(X_test,y_test) * len(np.unique(y))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19.9\n",
+      "1 loop, best of 1: 50.1 s per loop\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%timeit -n 1 -r 1\n",
+    "print decode(msrx)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:allensdk]",
+   "language": "python",
+   "name": "conda-env-allensdk-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}