From 1ed2c4dc0a4e361b525e6eb386b889f6a57c6144 Mon Sep 17 00:00:00 2001
From: Janhavi Mahajan <jamahaja@microsoft.com>
Date: Mon, 13 May 2019 18:14:31 -0400
Subject: [PATCH] feat(bug fix) updated snli notebook with to_lowercase_all()
 instead of to_lowercase() that expects a column name list. Fixed None object
 returning in to_lowercase when column name list is not passed

---
 .../01-prep-data/snli.ipynb                   | 25 +++++++++++--------
 utils_nlp/dataset/preprocess.py               |  2 +-
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/scenarios/sentence_similarity/01-prep-data/snli.ipynb b/scenarios/sentence_similarity/01-prep-data/snli.ipynb
index c886b1f..1fdb6d8 100644
--- a/scenarios/sentence_similarity/01-prep-data/snli.ipynb
+++ b/scenarios/sentence_similarity/01-prep-data/snli.ipynb
@@ -38,8 +38,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "System version: 3.6.8 |Anaconda, Inc.| (default, Dec 29 2018, 19:04:46) \n",
-      "[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)]\n"
+      "System version: 3.6.8 |Anaconda, Inc.| (default, Feb 21 2019, 18:30:04) [MSC v.1916 64 bit (AMD64)]\n"
      ]
     }
    ],
@@ -48,7 +47,7 @@
     "sys.path.append(\"../../../\")\n",
     "\n",
     "import os\n",
-    "from utils_nlp.dataset.preprocess import to_lowercase, to_nltk_tokens\n",
+    "from utils_nlp.dataset.preprocess import to_lowercase_all, to_nltk_tokens\n",
     "from utils_nlp.dataset import snli\n",
     "\n",
     "print(\"System version: {}\".format(sys.version))"
@@ -429,13 +428,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "[nltk_data] Downloading package punkt to /Users/caseyhong/nltk_data...\n",
+      "[nltk_data] Downloading package punkt to\n",
+      "[nltk_data]     C:\\Users\\jamahaja\\AppData\\Roaming\\nltk_data...\n",
       "[nltk_data]   Package punkt is already up-to-date!\n"
      ]
     }
    ],
    "source": [
-    "train_tok = to_nltk_tokens(to_lowercase(train))"
+    "train_tok = to_nltk_tokens(to_lowercase_all(train))"
    ]
   },
   {
@@ -574,11 +574,14 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "[nltk_data] Downloading package punkt to /Users/caseyhong/nltk_data...\n",
+      "[nltk_data] Downloading package punkt to\n",
+      "[nltk_data]     C:\\Users\\jamahaja\\AppData\\Roaming\\nltk_data...\n",
       "[nltk_data]   Package punkt is already up-to-date!\n",
-      "[nltk_data] Downloading package punkt to /Users/caseyhong/nltk_data...\n",
+      "[nltk_data] Downloading package punkt to\n",
+      "[nltk_data]     C:\\Users\\jamahaja\\AppData\\Roaming\\nltk_data...\n",
       "[nltk_data]   Package punkt is already up-to-date!\n",
-      "[nltk_data] Downloading package punkt to /Users/caseyhong/nltk_data...\n",
+      "[nltk_data] Downloading package punkt to\n",
+      "[nltk_data]     C:\\Users\\jamahaja\\AppData\\Roaming\\nltk_data...\n",
       "[nltk_data]   Package punkt is already up-to-date!\n"
      ]
     }
@@ -592,9 +595,9 @@
     "clean_dev = clean(dev, file_split=\"dev\")\n",
     "clean_test = clean(dev, file_split=\"test\")\n",
     "\n",
-    "train_tok = to_nltk_tokens(to_lowercase(clean_train))\n",
-    "dev_tok = to_nltk_tokens(to_lowercase(clean_dev))\n",
-    "test_tok = to_nltk_tokens(to_lowercase(clean_test))\n",
+    "train_tok = to_nltk_tokens(to_lowercase_all(clean_train))\n",
+    "dev_tok = to_nltk_tokens(to_lowercase_all(clean_dev))\n",
+    "test_tok = to_nltk_tokens(to_lowercase_all(clean_test))\n",
     "\n",
     "split_map = {'train': train_tok, 'dev': dev_tok, 'test': test_tok}\n",
     "for file_split, df in split_map.items():\n",
diff --git a/utils_nlp/dataset/preprocess.py b/utils_nlp/dataset/preprocess.py
index 1b6c5c3..8533980 100644
--- a/utils_nlp/dataset/preprocess.py
+++ b/utils_nlp/dataset/preprocess.py
@@ -32,7 +32,7 @@ def to_lowercase(df, column_names=[]):
         pd.DataFrame: Dataframe with columns with lowercase standardization.
     """
     if not column_names:
-        to_lowercase_all(df)
+        return to_lowercase_all(df)
     else:
         df[column_names] = df[column_names].applymap(
             lambda s: s.lower() if type(s) == str else s