Added Dockefile w/ python 3

Author: adelavega

Dockerfile

@@ -0,0 +1,8 @@
+FROM jupyter/scipy-notebook:latest
+
+COPY requirements.txt /tmp/
+RUN pip install --requirement /tmp/requirements.txt && \
+    fix-permissions $CONDA_DIR && \
+    fix-permissions /home/$NB_USER
+
+WORKDIR /usr/src/work

classification.py

@@ -1,13 +1,14 @@
 import numpy as np
-from tools import ProgressBar, mask_diagonal
+from tqdm import tqdm
+from tools import mask_diagonal
 from joblib import Parallel, delayed
 
 # Replace with a more basic sklearn function
 from neurosynth.analysis.classify import classify
 
 
 def classify_parallel(classifier, scoring, region_data, importance_function):
-    """ Parallel classification function. Used to classify for each region if study 
+    """ Parallel classification function. Used to classify for each region if study
     was activated or not (typically based on neurosynth features)
     classifier: sklearn classifier
     scoring: sklearn scoring function
@@ -31,15 +32,15 @@ def log_odds_ratio(clf):
 
 class RegionalClassifier(object):
 
-    """" Object used to classify on a region by region basis (from a cluster solution) 
-    if studies activated a region using Neurosynth features (e.g. topics) 
+    """" Object used to classify on a region by region basis (from a cluster solution)
+    if studies activated a region using Neurosynth features (e.g. topics)
     as classification features """
 
     def __init__(self, dataset, mask_img, classifier=None, cv='4-Fold',
                  thresh=0.05, thresh_low=0):
         """
         dataset - Neurosynth dataset
-        mask_img - Path to Nifti image containing discrete regions coded as levels 
+        mask_img - Path to Nifti image containing discrete regions coded as levels
         classifier - sklearn classifier
         cv - cross validation strategy
         thresh - Threshold used to determine if a study is considered to have activated a region
@@ -109,18 +110,15 @@ def classify(self, scoring='accuracy', n_jobs=1, importance_function=None):
             self.initalize_containers()
 
         print("Classifying...")
-        pb = ProgressBar(self.n_regions, start=True)
 
-        for index, output in enumerate(Parallel(n_jobs=n_jobs)(
-                delayed(classify_parallel)(
-                    self.classifier, scoring, region_data, importance_function) for region_data in self.data)):
+        for index, output in enumerate(
+          tqdm(Parallel(n_jobs=n_jobs)(delayed(classify_parallel)(self.classifier, scoring, region_data, importance_function) for region_data in self.data))):
             self.class_score[index] = output['score']
             self.importance[index] = output['importance']
             self.predictions[index] = output['predictions']
-            pb.next()
 
     def get_formatted_importances(self, feature_names=None):
-        """ Returns a pandas table of importances for each feature for each region. 
+        """ Returns a pandas table of importances for each feature for each region.
         Optionally takes new names for each feature (i.e. nickanames) """
         import pandas as pd
         if feature_names is None:

clustering.ipynb

@@ -37,7 +37,7 @@ def coactivation_contrast(dataset, infile, regions=None, target_thresh=0.05,
 
     affine = image.get_affine()
 
-    stat="pFgA_z_FDR_%s" % str(q)
+    stat="association-test_z_FDR_%s" % str(q)
 
     if regions == None:
         regions = np.arange(1, image.get_data().max() + 1)

coactivation.ipynb

@@ -22,12 +22,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true,
-    "deletable": true,
-    "editable": true
-   },
+   "execution_count": 1,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import zipfile\n",
@@ -63,7 +59,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.2"
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,

coactivation.py

@@ -23,11 +23,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
-   "source": ["%matplotlib inline\n",
+   "source": [
     "# Load a neurosynth dataset. If you generate your own dataset, you can try this with fewer or greater number of topics\n",
     "from neurosynth.base.dataset import Dataset\n",
     "dataset = Dataset.load(\"data/neurosynth_60_0.4.pkl\")"
@@ -36,9 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "from sklearn.naive_bayes import GaussianNB\n",
@@ -56,16 +52,31 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.6/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
+      "  \"This module will be removed in 0.20.\", DeprecationWarning)\n",
+      "/opt/conda/lib/python3.6/site-packages/sklearn/grid_search.py:43: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. This module will be removed in 0.20.\n",
+      "  DeprecationWarning)\n",
+      "100%|██████████| 3/3 [00:00<00:00, 8405.42it/s]"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Classifying...\n",
-      "[##########] 100%\n"
+      "Classifying...\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
      ]
     }
    ],
@@ -85,14 +96,12 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "array([ 0.63252944,  0.63061157,  0.68145715])"
+       "array([ 0.63538912,  0.6304816 ,  0.67899716])"
       ]
      },
      "execution_count": 4,
@@ -120,10 +129,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import pandas as pd\n",
@@ -168,9 +175,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stderr",
@@ -204,9 +209,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -226,9 +229,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -278,9 +279,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -324,9 +323,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -347,9 +344,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -370,9 +365,7 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -404,23 +397,23 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 2",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "python2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.11"
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }

index.ipynb

@@ -1,7 +1,9 @@
--e git://github.com/neurosynth/neurosynth.git#egg=neurosynth
+neurosynth
 nibabel==1.3.0
-numpy
+nilearn==0.3.1
+matplotlib==2.0
 joblib
 pandas
-nilearn
 seaborn
+scikit-learn==0.17
+tqdm

profiles.ipynb

@@ -1,39 +1,6 @@
 from sys import stdout
 import numpy as np
 
-class ProgressBar():
-    """" Custom Progress Bar used during classification process """
-    def __init__(self, total, start=False):
-        """
-        total - total number of events
-        start - automatically start when created? 
-        """
-        self.total = total
-        self.current = 0.0
-        self.last_int = 0
-        if start:
-            self.next()
-
-    def update_progress(self, progress):
-        display = '\r[{0}] {1}%'.format('#' * (progress / 10), progress)
-        stdout.write(display)
-        stdout.flush()
-
-    def next(self):
-        """ Increment progress bar"""
-        if not self.last_int == int((self.current) / self.total * 100):
-            self.update_progress(int((self.current) / self.total * 100))
-            self.last_int = int((self.current) / self.total * 100)
-
-        if self.current == self.total:
-            self.reset()
-        else:
-            self.current = self.current + 1
-
-    def reset(self):
-        print ""
-        self.current = 0.0
-
 def mask_diagonal(masked_array):
     """ Given a masked array, it returns the same array with the diagonals masked"""
     if len(masked_array.shape) == 3:
@@ -45,4 +12,4 @@ def mask_diagonal(masked_array):
             *map(np.arange, masked_array.shape), indexing='ij')
         masked_array.mask = (i == j)
 
-    return masked_array
+    return masked_array