Task1

.gitignore

@@ -157,3 +157,7 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+Data/
+Data/anonymized
+anonymized/

notebooks/parse_slack_data.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -33,17 +33,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 25,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: 'Data/anonymized\\\\channels.json'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\ezra2\\OneDrive\\Documents\\10Acadmy\\week0_starter_network_analysis\\notebooks\\parse_slack_data.ipynb Cell 3\u001b[0m line \u001b[0;36m6\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/notebooks/parse_slack_data.ipynb#W2sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m \u001b[39m# if rpath not in sys.path:\u001b[39;00m\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/notebooks/parse_slack_data.ipynb#W2sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m sys\u001b[39m.\u001b[39mpath\u001b[39m.\u001b[39minsert(\u001b[39m0\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mC:\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39mUsers\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39mezra2\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39mOneDrive\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39mDocuments\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39m10Acadmy\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39mweek0_starter_network_analysis\u001b[39m\u001b[39m\\\\\u001b[39;00m\u001b[39msrc\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/notebooks/parse_slack_data.ipynb#W2sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39msrc\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mloader\u001b[39;00m \u001b[39mimport\u001b[39;00m SlackDataLoader\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/notebooks/parse_slack_data.ipynb#W2sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39m# import src.utils as utils\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\ezra2\\OneDrive\\Documents\\10Acadmy\\week0_starter_network_analysis\\src\\__init__.py:3\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mloader\u001b[39;00m \u001b[39mimport\u001b[39;00m SlackDataLoader \n\u001b[0;32m      2\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mjson\u001b[39;00m\n\u001b[1;32m----> 3\u001b[0m data_loader \u001b[39m=\u001b[39m SlackDataLoader(\u001b[39m'\u001b[39;49m\u001b[39mData/anonymized\u001b[39;49m\u001b[39m'\u001b[39;49m)\n",
+      "File \u001b[1;32m~\\OneDrive\\Documents\\10Acadmy\\week0_starter_network_analysis\\src\\loader.py:38\u001b[0m, in \u001b[0;36mSlackDataLoader.__init__\u001b[1;34m(self, path)\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[39m\u001b[39m\u001b[39m'''\u001b[39;00m\n\u001b[0;32m     34\u001b[0m \u001b[39mpath: path to the slack exported data folder\u001b[39;00m\n\u001b[0;32m     35\u001b[0m \u001b[39m'''\u001b[39;00m\n\u001b[0;32m     37\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpath \u001b[39m=\u001b[39m path\n\u001b[1;32m---> 38\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mchannels \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mget_channels()\n\u001b[0;32m     39\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39musers \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mget_users()\n",
+      "File \u001b[1;32m~\\OneDrive\\Documents\\10Acadmy\\week0_starter_network_analysis\\src\\loader.py:67\u001b[0m, in \u001b[0;36mSlackDataLoader.get_channels\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     61\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mget_channels\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m     62\u001b[0m \u001b[39m    \u001b[39m\u001b[39m'''\u001b[39;00m\n\u001b[0;32m     63\u001b[0m \u001b[39m    write a function to get all the channels from the json file\u001b[39;00m\n\u001b[0;32m     64\u001b[0m \u001b[39m    '''\u001b[39;00m\n\u001b[1;32m---> 67\u001b[0m     \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39;49m(os\u001b[39m.\u001b[39;49mpath\u001b[39m.\u001b[39;49mjoin(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpath, \u001b[39m'\u001b[39;49m\u001b[39mchannels.json\u001b[39;49m\u001b[39m'\u001b[39;49m), \u001b[39m'\u001b[39;49m\u001b[39mr\u001b[39;49m\u001b[39m'\u001b[39;49m) \u001b[39mas\u001b[39;00m f:\n\u001b[0;32m     68\u001b[0m         channels \u001b[39m=\u001b[39m json\u001b[39m.\u001b[39mload(f)\n\u001b[0;32m     70\u001b[0m     \u001b[39mreturn\u001b[39;00m channels\n",
+      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'Data/anonymized\\\\channels.json'"
+     ]
+    }
+   ],
    "source": [
     "# Add parent directory to path to import modules from src\n",
     "rpath = os.path.abspath('..')\n",
-    "if rpath not in sys.path:\n",
-    "    sys.path.insert(0, rpath)\n",
+    "# if rpath not in sys.path:\n",
+    "sys.path.insert(0, 'C:\\\\Users\\\\ezra2\\\\OneDrive\\\\Documents\\\\10Acadmy\\\\week0_starter_network_analysis\\\\src')\n",
     "\n",
     "from src.loader import SlackDataLoader\n",
-    "import src.utils as utils"
+    "# import src.utils as utils"
    ]
   },
   {
@@ -95,7 +110,8 @@
     "    \"\"\"\n",
     "\n",
     "    # specify path to get json files\n",
-    "    combined = []\n",
+    "    combined = []#sa\n",
+    "    \n",
     "    for json_file in glob.glob(f\"{path_channel}*.json\"):\n",
     "        with open(json_file, 'r', encoding=\"utf8\") as slack_data:\n",
     "            combined.append(slack_data)\n",
@@ -359,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -368,7 +384,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -377,7 +393,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -386,7 +402,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -395,7 +411,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -444,7 +460,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

src/__init__1.ipynb

@@ -0,0 +1,58 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: 'Data/anonymized\\\\channels.json'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\ezra2\\OneDrive\\Documents\\10Acadmy\\week0_starter_network_analysis\\src\\__init__.ipynb Cell 1\u001b[0m line \u001b[0;36m9\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/src/__init__.ipynb#W4sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m sys\u001b[39m.\u001b[39mpath\u001b[39m.\u001b[39minsert(\u001b[39m1\u001b[39m,\u001b[39m\"\u001b[39m\u001b[39mC:/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/src\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m      <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/src/__init__.ipynb#W4sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39msrc\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mloader\u001b[39;00m \u001b[39mimport\u001b[39;00m SlackDataLoader\n\u001b[1;32m----> <a href='vscode-notebook-cell:/c%3A/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis/src/__init__.ipynb#W4sZmlsZQ%3D%3D?line=8'>9</a>\u001b[0m n\u001b[39m=\u001b[39mSlackDataLoader(\u001b[39m\"\u001b[39;49m\u001b[39mData/anonymized\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n",
+      "File \u001b[1;32mC:\\Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis\\src\\loader.py:38\u001b[0m, in \u001b[0;36mSlackDataLoader.__init__\u001b[1;34m(self, path)\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[39m\u001b[39m\u001b[39m'''\u001b[39;00m\n\u001b[0;32m     34\u001b[0m \u001b[39mpath: path to the slack exported data folder\u001b[39;00m\n\u001b[0;32m     35\u001b[0m \u001b[39m'''\u001b[39;00m\n\u001b[0;32m     37\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpath \u001b[39m=\u001b[39m path\n\u001b[1;32m---> 38\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mchannels \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mget_channels()\n\u001b[0;32m     39\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39musers \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mget_users()\n",
+      "File \u001b[1;32mC:\\Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis\\src\\loader.py:67\u001b[0m, in \u001b[0;36mSlackDataLoader.get_channels\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     61\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mget_channels\u001b[39m(\u001b[39mself\u001b[39m):\n\u001b[0;32m     62\u001b[0m \u001b[39m    \u001b[39m\u001b[39m'''\u001b[39;00m\n\u001b[0;32m     63\u001b[0m \u001b[39m    write a function to get all the channels from the json file\u001b[39;00m\n\u001b[0;32m     64\u001b[0m \u001b[39m    '''\u001b[39;00m\n\u001b[1;32m---> 67\u001b[0m     \u001b[39mwith\u001b[39;00m \u001b[39mopen\u001b[39;49m(os\u001b[39m.\u001b[39;49mpath\u001b[39m.\u001b[39;49mjoin(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mpath, \u001b[39m'\u001b[39;49m\u001b[39mchannels.json\u001b[39;49m\u001b[39m'\u001b[39;49m), \u001b[39m'\u001b[39;49m\u001b[39mr\u001b[39;49m\u001b[39m'\u001b[39;49m) \u001b[39mas\u001b[39;00m f:\n\u001b[0;32m     68\u001b[0m         channels \u001b[39m=\u001b[39m json\u001b[39m.\u001b[39mload(f)\n\u001b[0;32m     70\u001b[0m     \u001b[39mreturn\u001b[39;00m channels\n",
+      "\u001b[1;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'Data/anonymized\\\\channels.json'"
+     ]
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "sys.path.insert(1,\"C:/Users/ezra2/OneDrive/Documents/10Acadmy/week0_starter_network_analysis\")\n",
+    "\n",
+    "\n",
+    "\n",
+    "from src.loader import SlackDataLoader\n",
+    "\n",
+    "n=SlackDataLoader(\"Data/anonymized\")\n",
+    "\n",
+    " \n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/loader.py

@@ -13,6 +13,7 @@
 # Create wrapper classes for using slack_sdk in place of slacker
 class SlackDataLoader:
     '''
+    n=SlackDataLoader('Data/anonymized')
     Slack exported data IO class.
 
     When you open slack exported ZIP file, each channel or direct message 
@@ -32,10 +33,21 @@ def __init__(self, path):
         '''
         path: path to the slack exported data folder
         '''
+
         self.path = path
         self.channels = self.get_channels()
-        self.users = self.get_ussers()
-
+        self.users = self.get_users()
+    def get_channel_sub_files(self):
+        channels_files={}
+        BS=r"\""[0]
+        for (current_folder,folders_in_current_folder,files_in_current_folder) in os.walk(self.path):
+            if(len(folders_in_current_folder) == 0):
+                current_channel_name=str(current_folder).split(BS)[1]
+                channels_files[current_channel_name]=files_in_current_folder
+        return json.dumps(channels_files)
+
+
+
 
     def get_users(self):
         '''
@@ -50,18 +62,39 @@ def get_channels(self):
         '''
         write a function to get all the channels from the json file
         '''
+
+
         with open(os.path.join(self.path, 'channels.json'), 'r') as f:
             channels = json.load(f)
 
         return channels
-
+    def get_channel_sub_file(self,channel_name):
+        channel_sub_files=json.loads(self.get_channel_sub_files())
+        return channel_sub_files[channel_name]
+    def get_channel_messages_by_day(self,current_day_path):
+        with open(current_day_path,'r') as f:
+            message=json.load(f)
+        return message
     def get_channel_messages(self, channel_name):
+        channel_path=os.path.join(self.path,channel_name)
         '''
         write a function to get all the messages from a channel
 
         '''
+        message={}
+        daily_channel_messages_file=self.get_channel_sub_file(channel_name)
+        for current_day in daily_channel_messages_file:
+            current_day_path=os.path.join(channel_path,current_day)
+            message[current_day]=(self.get_channel_messages_by_day(current_day_path))
+        #to see if the json object is correct write into file 
+        #  with open("sample.json", "w") as outfile:
+        #     outfile.write(json.dumps(message))
+        return json.dumps(message)
+
+
+
 
-    # 
+
     def get_user_map(self):
         '''
         write a function to get a map between user id and user name

src/new.py

@@ -0,0 +1,39 @@
+from loader import SlackDataLoader 
+import json
+data_loader = SlackDataLoader('Data/anonymized')
+
+# print(data_loader.get_channel_sub_files())
+(data_loader.get_channel_messages("week-11-group4"))
+
+
+
+
+
+
+
+# # slack_data = data_loader.get_users()
+# cha=data_loader.get_channels()[0]['name']
+# data_loader.get_channel_messages(cha)
+# import os
+# import json
+# folder_path="Data/anonymized"
+# # print(folder_path)
+
+# channels_files={}
+# for (current_folder,folders_in_current_folder,files_in_current_folder) in os.walk(folder_path):
+#     if(len(folders_in_current_folder) == 0):
+#         BS=r"\""[0]
+#         # print("=======================================")
+#         # print(f'*****current_folder {str(current_folder).split(BS)[1]}')
+#         # print(f'*****folders_in_current_folder {str(folders_in_current_folder)}')
+#         # print(f'*****files_in_current_folder {str(files_in_current_folder)}')
+#         # print("=======================================")
+#         current_channel=str(current_folder).split(BS)[1]
+#         # channels_files[current_channel]={}
+#         channels_files[current_channel]=files_in_current_folder
+#         # print(current_channel)
+
+
+# # print(json.loads(channels_files))
+# obj = json.dumps(channels_files)
+# print(obj)