Update fake_news_cleaning.ipynb

Shannon-Watts · Aug 18, 2022 · c66209f · c66209f
1 parent 344ac6c
commit c66209f
Showing 1 changed file with 16 additions and 16 deletions.
diff --git a/fake_news_cleaning.ipynb b/fake_news_cleaning.ipynb
@@ -642,12 +642,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [],
    "source": [
     "import re\n",
-    "URLS = r'(https://)'\n",
+    "URLS = r'(https?://\\S+)'\n",
     "true_copy = true_df\n",
     "fake_copy = fake_df\n",
     "true_copy['urlcount'] = true_df.text.apply(lambda x: re.findall(URLS, x)).str.len()\n",
@@ -656,7 +656,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [
     {
@@ -666,7 +666,7 @@
        "Name: urlcount, dtype: int64"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -677,7 +677,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
@@ -686,7 +686,7 @@
        "3299"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -883,12 +883,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [],
    "source": [
     "import re\n",
-    "URLS = r'(https://)'\n",
+    "URLS = r'(https?://\\S+)'\n",
     "true_copy2 = true_df.copy()\n",
     "fake_copy2 = fake_df.copy()\n",
     "true_copy2['urlcount'] = true_copy2['date'].apply(lambda x: re.findall(URLS, x)).str.len()\n",
@@ -897,7 +897,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [
     {
@@ -906,7 +906,7 @@
        "9"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -917,7 +917,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 50,
    "metadata": {},
    "outputs": [
     {
@@ -931,7 +931,7 @@
        "Name: 21870, dtype: object"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -942,7 +942,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [
     {
@@ -1085,7 +1085,7 @@
        "21870  https://fedup.wpengine.com/wp-content/uploads/...         1  "
       ]
      },
-     "execution_count": 20,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1096,7 +1096,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [
     {
@@ -1264,7 +1264,7 @@
        "[23481 rows x 5 columns]"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 52,
      "metadata": {},
      "output_type": "execute_result"
     }