Moved datafile pointers; new progress_bar; better error on unzip

conx/datasets/_colors.py

@@ -3,7 +3,7 @@
 import csv
 
 def colors(*args, path='colors.csv',
-           url="https://raw.githubusercontent.com/Calysto/conx/master/data/colors.csv",
+           url="https://raw.githubusercontent.com/Calysto/conx-data/master/colors/colors.csv",
            **kwargs):
     dataset = cx.Dataset()
     from keras.utils import get_file

conx/datasets/_fingers.py

@@ -5,7 +5,7 @@ def fingers(*args, path='fingers.npz', **kwargs):
     dataset = cx.Dataset()
     inputs, labels = load_dataset_npz(
         path,
-        "https://raw.githubusercontent.com/Calysto/conx/master/data/fingers.npz")
+        "https://raw.githubusercontent.com/Calysto/conx-data/master/fingers/fingers.npz")
     inputs = inputs.astype('float32')
     inputs /= 255
     make_target_vector = lambda label: [int(label == n) for n in range(6)]

conx/datasets/_gridfonts.py

@@ -4,7 +4,7 @@
 
 def gridfonts(*args, **kwargs):
     dataset = cx.Dataset()
-    url = "https://raw.githubusercontent.com/Calysto/conx/master/data/gridfonts.npy"
+    url = "https://raw.githubusercontent.com/Calysto/conx-data/master/gridfonts/gridfonts.npy"
     path = get_file("gridfonts.npy", origin=url)
     ds = np.load(path)
     ## [letters, labels]
@@ -18,12 +18,12 @@ def gridfonts(*args, **kwargs):
 
 http://goosie.cogsci.indiana.edu/pub/gridfonts.data
 
-![Gridfont Grid](https://github.com/Calysto/conx/raw/master/data/grid.png)
+![Gridfont Grid](https://github.com/Calysto/conx-data/raw/master/gridfonts/grid.png)
 
 These data have been processed to make them neural
 network friendly:
 
-https://github.com/Calysto/conx/blob/master/data/gridfonts.py
+https://github.com/Calysto/conx-data/blob/master/gridfonts/gridfonts.py
 
 The dataset is composed of letters on a 25 row x 9 column
 grid. The inputs and targets are identical, and the labels
@@ -37,7 +37,7 @@ def gridfonts(*args, **kwargs):
 
 def figure_ground_a(*args, **kwargs):
     dataset = cx.Dataset()
-    url = "https://raw.githubusercontent.com/Calysto/conx/master/data/figure_ground_a.npy"
+    url = "https://raw.githubusercontent.com/Calysto/conx-data/master/gridfonts/figure_ground_a.npy"
     path = get_file("figure_ground_a.npy", origin=url)
     ds = np.load(path)
     ## [[[letter], [brim, body]], ...]
@@ -51,12 +51,12 @@ def figure_ground_a(*args, **kwargs):
 
 http://goosie.cogsci.indiana.edu/pub/gridfonts.data
 
-![Gridfont Grid](https://github.com/Calysto/conx/raw/master/data/grid.png)
+![Gridfont Grid](https://github.com/Calysto/conx-data/raw/master/gridfonts/grid.png)
 
 These data (all the letter A) have been processed to make them neural
 network friendly:
 
-https://github.com/Calysto/conx/blob/master/data/gridfonts.py
+https://github.com/Calysto/conx-data/blob/master/gridfonts/gridfonts.py
 
 The brim and body parts have been idenified manually.  The dataset is
 composed of letters on a 17 row x 9 column grid (4 lines not used on

conx/datasets/_mnist.py

@@ -14,7 +14,7 @@
 10, corresponding to the digit classification categories zero through
 nine.  Some example MNIST images are shown below:
 
-![MNIST Images](https://github.com/Calysto/conx/raw/master/data/mnist_images.png)
+![MNIST Images](https://github.com/Calysto/conx-data/raw/master/mnist/mnist_images.png)
 """
 
 def mnist_h5(*args, **kwargs):
@@ -24,7 +24,7 @@ def mnist_h5(*args, **kwargs):
     import h5py
 
     path = "mnist.h5"
-    url = "https://raw.githubusercontent.com/Calysto/conx/master/data/mnist.h5"
+    url = "https://raw.githubusercontent.com/Calysto/conx-data/master/mnist/mnist.h5"
     path = get_file(path, origin=url)
     h5 = h5py.File(path, "r")
     dataset = cx.Dataset()

conx/datasets/cmu_faces.py

@@ -5,7 +5,7 @@ def cmu_faces_full_size(*args, path="cmu_faces_full_size.npz", **kwargs):
     dataset = cx.Dataset()
     inputs, labels = load_dataset_npz(
         path,
-        "https://raw.githubusercontent.com/Calysto/conx/master/data/cmu_faces_full_size.npz")
+        "https://raw.githubusercontent.com/Calysto/conx-data/master/cmu_faces/cmu_faces_full_size.npz")
     dataset.name = "CMU Faces, full-size"
     dataset.description = """
 Original source: http://archive.ics.uci.edu/ml/datasets/cmu+face+images
@@ -16,7 +16,7 @@ def cmu_faces_quarter_size(*args, path="cmu_faces_quarter_size.npz", **kwargs):
     dataset = cx.Dataset()
     inputs, labels = load_dataset_npz(
         path,
-        "https://raw.githubusercontent.com/Calysto/conx/master/data/cmu_faces_quarter_size.npz")
+        "https://raw.githubusercontent.com/Calysto/conx-data/master/cmu_faces/cmu_faces_quarter_size.npz")
     dataset.name = "CMU Faces, quarter-size"
     dataset.description = """
 Original source: http://archive.ics.uci.edu/ml/datasets/cmu+face+images
@@ -27,7 +27,7 @@ def cmu_faces_half_size(*args, path="cmu_faces_half_size.npz", **kwargs):
     dataset = cx.Dataset()
     inputs, labels = load_dataset_npz(
         path,
-        "https://raw.githubusercontent.com/Calysto/conx/master/data/cmu_faces_half_size.npz")
+        "https://raw.githubusercontent.com/Calysto/conx-data/master/cmu_faces/cmu_faces_half_size.npz")
     dataset.name = "CMU Faces, half-size"
     dataset.description = """
 Original source: http://archive.ics.uci.edu/ml/datasets/cmu+face+images

conx/utils.py

@@ -55,15 +55,19 @@
 
 def progress_bar(*args, **kwargs):
     if _PROGRESS_BAR is None:
-        return items
+        if args:
+            return lambda i: i
+        else:
+            return None
     elif _PROGRESS_BAR == "notebook":
-        tqdm.tqdm_notebook(*args, **kwargs)
+        return tqdm.tqdm_notebook(*args, **kwargs)
     elif _PROGRESS_BAR == "standard":
-        tqdm.tqdm(*args, **kwargs)
+        return tqdm.tqdm(*args, **kwargs)
     else:
-        return items
+        raise Exception("no such progress bar: use None, 'notebook', or 'standard'")
 
 def set_progress_bar(mode):
+    global _PROGRESS_BAR
     if mode in [None, 'notebook', 'standard']:
         _PROGRESS_BAR = mode
     else:
@@ -569,7 +573,11 @@ def download(url, directory="./", force=False, unzip=True, filename=None,
         print("Using cached %s as '%s'." % (url, file_path))
     ## Now, if it is a zip file, check to unzip:
     if file_path.endswith(".zip") and os.path.isfile(file_path):
-        zip_ref = zipfile.ZipFile(file_path, 'r')
+        try:
+            zip_ref = zipfile.ZipFile(file_path, 'r')
+        except zipfile.BadZipFile:
+            print("URL appears to be invalid for zip file. Try deleteing the file and re-trying.")
+            return
         # first, count existing unzipped files:
         total_count = 0
         for name in zip_ref.namelist():