Merge pull request #52 from jmborr/51_update_docs_data_repo

modify docs to instruct how to download the data repository

HISTORY.rst

@@ -2,6 +2,11 @@
 History
 =======
 
+0.1.5 ()
+--------
+
+* Update notebook and docs with data repo (PR #51)
+
 0.1.4 (2018-02-11)
 ------------------
 

docs/installation.rst

@@ -14,7 +14,7 @@ To install idpflex, run this command in your terminal:
 
     $ pip install idpflex
 
-This is the preferred method to install idpflex, as it will always install the most recent stable release. 
+This is the preferred method to install idpflex, as it will always install the most recent stable release.
 
 If you don't have `pip`_ installed, this `Python installation guide`_ can guide
 you through the process.
@@ -49,3 +49,42 @@ Once you have a copy of the source, you can install it with:
 
 .. _Github repo: https://github.com/jmborr/idpflex
 .. _tarball: https://github.com/jmborr/idpflex/tarball/master
+
+
+Testing & Tutorials Data
+------------------------
+
+The external repository `idpflex_data <https://github.com/jmborr/idpflex_data>`
+contains all data files used in testing, examples, and tutorials.
+There are several ways to obtain this dataset:
+
+1. Clone the repository with a git command in a terminal:
+
+.. code :: bash
+
+    cd some/directory/
+    git clone https://github.com/jmborr/idfplex_data.git
+
+2. Download all data files as a zip file using GitHub's web interface:
+
+.. image:: images/data_download_zip.png
+    :width: 800px
+    :align: center
+    :alt: download dataset as zipped file
+
+3. Download individual files using GitHub's web interface by browsing to the
+file. If the file is in binary format, then click in Download button:
+
+.. image:: images/data_download_file.png
+    :width: 800px
+    :align: center
+    :alt: download dataset as zipped file
+
+If the file is in ASCII format, you must first click in the `Raw` view. After
+this you can right-click and `Save as`.
+
+.. image:: images/data_download_ascii_file.png
+    :width: 800px
+    :align: center
+    :alt: download dataset as zipped file
+

notebooks/.ipynb_checkpoints/hiAPP_clustering-checkpoint.ipynb

@@ -28,6 +28,7 @@
     "import matplotlib.pyplot as plt\n",
     "plt.ion()\n",
     "\n",
+    "import os\n",
     "import sys\n",
     "import subprocess\n",
     "import numpy as np\n",
@@ -46,6 +47,39 @@
     "from idpflex.bayes import fit_to_depth"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Donwload Data\n",
+    "\n",
+    "It's assumed <code>git</code> is installed in your system. Otherwise,\n",
+    "[follow instructions](http://idpflex.readthedocs.io/en/latest/installation.html#testing-tutorials-data)\n",
+    "to download and unpack your data to <code>/tmp/idpflex_data</code>."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%bash\n",
+    "idpflex_data_dir=\"/tmp/idpflex_data\"\n",
+    "git clone https://github.com/jmborr/idpflex_data ${idpflex_data_dir}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "idpflex_data_dir = '/tmp/idpflex_data'\n",
+    "data_dir = os.path.join(idpflex_data_dir, 'data', 'simulation')\n",
+    "print(data_dir)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -61,7 +95,8 @@
    },
    "outputs": [],
    "source": [
-    "simulation = mda.Universe('../tests/data/simulation/hiAPP.pdb', '../tests/data/simulation/hiAPP.xtc')\n",
+    "simulation = mda.Universe(os.path.join(data_dir, 'hiAPP.pdb'),\n",
+    "                          os.path.join(data_dir, 'hiAPP.xtc'))\n",
     "print('Number of frames in trajectory is ', simulation.trajectory.n_frames)"
    ]
   },
@@ -449,7 +484,7 @@
    "source": [
     "node_ids = [188, 190, 192]  # ID's for the clusters matching the experimental profile \n",
     "for id in node_ids:\n",
-    "    pdb_list = [pdb_names[leaf_id) for leaf_id in cl.tree[id].leaf_ids]\n",
+    "    pdb_list = [pdb_names[leaf_id] for leaf_id in cl.tree[id].leaf_ids]\n",
     "    open('/tmp/node{}_pdblist.txt'.format(id), 'w').write('\\n'.join(pdb_list))"
    ]
   },

notebooks/hiAPP_clustering.ipynb

@@ -28,6 +28,7 @@
     "import matplotlib.pyplot as plt\n",
     "plt.ion()\n",
     "\n",
+    "import os\n",
     "import sys\n",
     "import subprocess\n",
     "import numpy as np\n",
@@ -46,6 +47,39 @@
     "from idpflex.bayes import fit_to_depth"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Donwload Data\n",
+    "\n",
+    "It's assumed <code>git</code> is installed in your system. Otherwise,\n",
+    "[follow instructions](http://idpflex.readthedocs.io/en/latest/installation.html#testing-tutorials-data)\n",
+    "to download and unpack your data to <code>/tmp/idpflex_data</code>."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%bash\n",
+    "idpflex_data_dir=\"/tmp/idpflex_data\"\n",
+    "git clone https://github.com/jmborr/idpflex_data ${idpflex_data_dir}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "idpflex_data_dir = '/tmp/idpflex_data'\n",
+    "data_dir = os.path.join(idpflex_data_dir, 'data', 'simulation')\n",
+    "print(data_dir)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -61,7 +95,8 @@
    },
    "outputs": [],
    "source": [
-    "simulation = mda.Universe('../tests/data/simulation/hiAPP.pdb', '../tests/data/simulation/hiAPP.xtc')\n",
+    "simulation = mda.Universe(os.path.join(data_dir, 'hiAPP.pdb'),\n",
+    "                          os.path.join(data_dir, 'hiAPP.xtc'))\n",
     "print('Number of frames in trajectory is ', simulation.trajectory.n_frames)"
    ]
   },
@@ -449,7 +484,7 @@
    "source": [
     "node_ids = [188, 190, 192]  # ID's for the clusters matching the experimental profile \n",
     "for id in node_ids:\n",
-    "    pdb_list = [pdb_names[leaf_id) for leaf_id in cl.tree[id].leaf_ids]\n",
+    "    pdb_list = [pdb_names[leaf_id] for leaf_id in cl.tree[id].leaf_ids]\n",
     "    open('/tmp/node{}_pdblist.txt'.format(id), 'w').write('\\n'.join(pdb_list))"
    ]
   },