From 7bfde8e5cc7dd9efb1d2fe466b3e7eafd027d88a Mon Sep 17 00:00:00 2001
From: Connor Olding <cloningdonor@gmail.com>
Date: Thu, 15 Mar 2018 02:10:28 +0100
Subject: [PATCH] rewrite main to dump tables instead

---
 README.md          | 67 +++++++++-------------------------------------
 mnists/__main__.py | 22 ++++++++++-----
 2 files changed, 28 insertions(+), 61 deletions(-)

diff --git a/README.md b/README.md
index 725515f..bbe66a4 100644
--- a/README.md
+++ b/README.md
@@ -34,62 +34,19 @@ pass `flatten=True` to `mnists.prepare` to get (n, 784).
 
 ## datasets
 
-in alphabetical order:
-
-### [emnist][emnist]
-
- *  `emnist_balanced`  
-    train images shape: (112800, 1, 28, 28)  
-    train labels shape: (112800, 47)  
-    test images shape: (18800, 1, 28, 28)  
-    test labels shape: (18800, 47)  
-
- *  `emnist_byclass`  
-    train images shape: (697932, 1, 28, 28)  
-    train labels shape: (697932, 62)  
-    test images shape: (116323, 1, 28, 28)  
-    test labels shape: (116323, 62)  
-
- *  `emnist_bymerge`  
-    train images shape: (697932, 1, 28, 28)  
-    train labels shape: (697932, 47)  
-    test images shape: (116323, 1, 28, 28)  
-    test labels shape: (116323, 47)  
-
- *  `emnist_digits`  
-    train images shape: (240000, 1, 28, 28)  
-    train labels shape: (240000, 10)  
-    test images shape: (40000, 1, 28, 28)  
-    test labels shape: (40000, 10)  
-
- *  `emnist_letters`  
-    train images shape: (124800, 1, 28, 28)  
-    train labels shape: (124800, 26)  
-    test images shape: (20800, 1, 28, 28)  
-    test labels shape: (20800, 26)  
-
- *  `emnist_mnist`  
-    train images shape: (60000, 1, 28, 28)  
-    train labels shape: (60000, 10)  
-    test images shape: (10000, 1, 28, 28)  
-    test labels shape: (10000, 10)  
-
-### [fashion-mnist][fashion-mnist]
-
- *  `fashion_mnist`  
-    train images shape: (60000, 1, 28, 28)  
-    train labels shape: (60000, 10)  
-    test images shape: (10000, 1, 28, 28)  
-    test labels shape: (10000, 10)  
-
-### [mnist][mnist]
-
- *  `mnist`  
-    train images shape: (60000, 1, 28, 28)  
-    train labels shape: (60000, 10)  
-    test images shape: (10000, 1, 28, 28)  
-    test labels shape: (10000, 10)  
+in alphabetical order, using default `mnists.prepare` parameters:
 
 [emnist]: //www.nist.gov/itl/iad/image-group/emnist-dataset
 [fashion-mnist]: //github.com/zalandoresearch/fashion-mnist
 [mnist]: http://yann.lecun.com/exdb/mnist/
+
+| dataset              | train images shape   | train labels shape   | test images shape    | test labels shape    |
+| :---                 | ---:                 | ---:                 | ---:                 | ---:                 |
+| emnist\_balanced     | (112800, 1, 28, 28)  | (112800, 47)         | (18800, 1, 28, 28)   | (18800, 47)          |
+| emnist\_byclass      | (697932, 1, 28, 28)  | (697932, 62)         | (116323, 1, 28, 28)  | (116323, 62)         |
+| emnist\_bymerge      | (697932, 1, 28, 28)  | (697932, 47)         | (116323, 1, 28, 28)  | (116323, 47)         |
+| emnist\_digits       | (240000, 1, 28, 28)  | (240000, 10)         | (40000, 1, 28, 28)   | (40000, 10)          |
+| emnist\_letters      | (124800, 1, 28, 28)  | (124800, 26)         | (20800, 1, 28, 28)   | (20800, 26)          |
+| emnist\_mnist        | (60000, 1, 28, 28)   | (60000, 10)          | (10000, 1, 28, 28)   | (10000, 10)          |
+| fashion\_mnist       | (60000, 1, 28, 28)   | (60000, 10)          | (10000, 1, 28, 28)   | (10000, 10)          |
+| mnist                | (60000, 1, 28, 28)   | (60000, 10)          | (10000, 1, 28, 28)   | (10000, 10)          |
diff --git a/mnists/__main__.py b/mnists/__main__.py
index 168f382..b9f3d8f 100644
--- a/mnists/__main__.py
+++ b/mnists/__main__.py
@@ -1,13 +1,23 @@
 from . import metadata, prepare
 
 
-names = ("train images", "train labels", "test images", "test labels")
+headers = ("dataset",
+           "train images shape",
+           "train labels shape",
+           "test images shape",
+           "test labels shape")
+
+row = "| {:<20} | {:<20} | {:<20} | {:<20} | {:<20} |"
+
+separators = (":---", "---:", "---:", "---:", "---:")
+
+print(row.format(*headers))
+print(row.format(*separators))
 
 for name in metadata.keys():
     # verify every dataset, downloading if necessary.
-    # print out the shapes for use in the README.
-    print(f" *  `{name}`  ")
+    # print out the shape table for use in the README.
     data = prepare(name)
-    for name, dat in zip(names, data):
-        print(f"    {name} shape: {dat.shape}  ")
-    print()
+    row_data = [name.replace("_", "\\_")]
+    row_data += [str(array.shape) for array in data]
+    print(row.format(*row_data))