add notebook to test app

tests/notebook.ipynb

@@ -36,10 +36,10 @@
     "    \"normalize_bullet_points\",\n",
     "    \"normalize_hyphenated_words\",\n",
     "    \"normalize_quotation_marks\",\n",
+    "    \"normalize_useless_spaces\",\n",
     "    \"normalize_repeating_words\",\n",
     "    \"normalize_repeating_chars\",\n",
     "    \"normalize_whitespaces\",\n",
-    "    \"normalize_useless_spaces\",\n",
     "    # \"replace_currency_symbols\",\n",
     "    # \"replace_emails\",\n",
     "    # \"replace_emojis\",\n",
@@ -66,20 +66,20 @@
    "source": [
     "post_steps = [\n",
     "    \"lowercase\",\n",
-    "    \"replace_currency_symbols\",\n",
-    "    \"replace_urls\",\n",
-    "    \"replace_emails\",\n",
-    "    \"replace_user_handles\",\n",
-    "    \"replace_hashtags\",\n",
-    "    \"replace_emojis\",\n",
+    "    # \"replace_currency_symbols\",\n",
+    "    # \"replace_urls\",\n",
+    "    # \"replace_emails\",\n",
+    "    # \"replace_user_handles\",\n",
+    "    # \"replace_hashtags\",\n",
+    "    # \"replace_emojis\",\n",
     "    # \"replace_phone_numbers\",\n",
     "    # \"replace_numbers\",\n",
-    "    \"remove_accents\",\n",
-    "    \"remove_brackets\",\n",
     "    \"remove_html_tags\",\n",
+    "    \"remove_accents\",\n",
+    "    # \"remove_brackets\",\n",
     "    \"remove_non_words\",\n",
-    "    \"remove_numbers\",\n",
-    "    \"remove_punctuation\",\n",
+    "    # \"remove_numbers\",\n",
+    "    # \"remove_punctuation\",\n",
     "    \"normalize_repeating_words\",\n",
     "    \"normalize_repeating_chars\",\n",
     "    \"normalize_useless_spaces\",\n",
@@ -172,7 +172,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -303,7 +303,7 @@
        "[5000 rows x 3 columns]"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -314,7 +314,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -325,16 +325,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[1, 14, 2, 3, 4, 23, 22, 5, 21, 24]"
+       "[1, 14, 2, 3, 4, 21, 23, 22, 5, 24]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -345,16 +345,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[0, 7, 6, 8, 13, 10, 9, 15, 16, 17, 19, 20, 18, 23, 22, 21, 24]"
+       "[0, 17, 15, 19, 23, 22, 21, 24]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -381,6 +381,44 @@
     "list(PreprocessingPipeline.lemmatization_component().keys())"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_re_non_words = re.compile(\"[^A-Za-z]+\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Mimmo '"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "_re_non_words.sub(\" \", \"Mimmo23\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,