Task 2

.gitignore

@@ -12,7 +12,7 @@ conf/**/*credentials*
 # ignore everything in the following folders
 data/**
 logs/**
-
+anonymized/
 # except their sub-folders
 !data/**/
 !logs/**/

notebooks/parse_slack_data.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -33,17 +33,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<src.loader.SlackDataLoader object at 0x000001ABB280D210>\n"
+     ]
+    }
+   ],
    "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",
     "\n",
     "from src.loader import SlackDataLoader\n",
-    "import src.utils as utils"
+    "import src.utils as utils\n",
+    "\n",
+    "\n",
+    "data_loader =  SlackDataLoader('C:/Users/zzz/Desktop/week0/week0_starter_network_analysis/anonymized')\n",
+    "print(data_loader)"
    ]
   },
   {
@@ -430,7 +442,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -444,7 +456,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

src/config.py

@@ -1,12 +1,12 @@
-from __future__ import print_function
-import argparse
-
-parser = argparse.ArgumentParser(description='cmdArgs')
-parser.add_argument('--output', type=str, default='slack_data.csv',
-                help='filename to write analysis output in CSV format')
-parser.add_argument('--path', required=True, type=str, help='directory where slack data reside')
-parser.add_argument('--channel', type=str, default='', help='which channel we parsing')
-parser.add_argument('--userfile', type=str, default='users.json', help='users profile information')
-
-cfg = parser.parse_args()
+from __future__ import print_function
+import argparse
+
+parser = argparse.ArgumentParser(description='cmdArgs')
+parser.add_argument('slack_data.csv', type=str, default='slack_data.csv',
+                help='filename to write analysis output in CSV format')
+parser.add_argument('anonymized', required=True, type=str, help='directory where slack data reside')
+parser.add_argument('--channel', type=str, default='', help='which channel we parsing')
+parser.add_argument('--userfile', type=str, default='users.json', help='users profile information')
+
+cfg = parser.parse_args()
 # print(cfg)

src/loader.py

@@ -1,84 +1,84 @@
-import json
-import argparse
-import os
-import io
-import shutil
-import copy
-from datetime import datetime
-from pick import pick
-from time import sleep
-
-
-
-# Create wrapper classes for using slack_sdk in place of slacker
-class SlackDataLoader:
-    '''
-    Slack exported data IO class.
-
-    When you open slack exported ZIP file, each channel or direct message 
-    will have its own folder. Each folder will contain messages from the 
-    conversation, organised by date in separate JSON files.
-
-    You'll see reference files for different kinds of conversations: 
-    users.json files for all types of users that exist in the slack workspace
-    channels.json files for public channels, 
-    
-    These files contain metadata about the conversations, including their names and IDs.
-
-    For secruity reason, we have annonymized names - the names you will see are generated using faker library.
-    
-    '''
-    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()
-    
-
-    def get_users(self):
-        '''
-        write a function to get all the users from the json file
-        '''
-        with open(os.path.join(self.path, 'users.json'), 'r') as f:
-            users = json.load(f)
-
-        return users
-    
-    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_messages(self, channel_name):
-        '''
-        write a function to get all the messages from a channel
-        
-        '''
-
-    # 
-    def get_user_map(self):
-        '''
-        write a function to get a map between user id and user name
-        '''
-        userNamesById = {}
-        userIdsByName = {}
-        for user in self.users:
-            userNamesById[user['id']] = user['name']
-            userIdsByName[user['name']] = user['id']
-        return userNamesById, userIdsByName        
-
-
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description='Export Slack history')
-
-    
-    parser.add_argument('--zip', help="Name of a zip file to import")
-    args = parser.parse_args()
+import json
+import argparse
+import os
+import io
+import shutil
+import copy
+from datetime import datetime
+from pick import pick
+from time import sleep
+
+
+
+# Create wrapper classes for using slack_sdk in place of slacker
+class SlackDataLoader:
+    '''
+    Slack exported data IO class.
+
+    When you open slack exported ZIP file, each channel or direct message 
+    will have its own folder. Each folder will contain messages from the 
+    conversation, organised by date in separate JSON files.
+
+    You'll see reference files for different kinds of conversations: 
+    users.json files for all types of users that exist in the slack workspace
+    channels.json files for public channels, 
+
+    These files contain metadata about the conversations, including their names and IDs.
+
+    For secruity reason, we have annonymized names - the names you will see are generated using faker library.
+
+    '''
+    def __init__(self, path):
+        '''
+        path: path to the slack exported data folder
+        '''
+        self.path = path
+        self.channels = self.get_channels()
+        self.users = self.get_users()
+
+
+    def get_users(self):
+        '''
+        write a function to get all the users from the json file
+        '''
+        with open(os.path.join(self.path, 'users.json'), 'r') as f:
+            users = json.load(f)
+
+        return users
+
+    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_messages(self, channel_name):
+        '''
+        write a function to get all the messages from a channel
+
+        '''
+
+    # 
+    def get_user_map(self):
+        '''
+        write a function to get a map between user id and user name
+        '''
+        userNamesById = {}
+        userIdsByName = {}
+        for user in self.users:
+            userNamesById[user['id']] = user['name']
+            userIdsByName[user['name']] = user['id']
+        return userNamesById, userIdsByName        
+
+
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Export Slack history')
+
+
+    parser.add_argument('--zip', help="Name of a zip file to import")
+    args = parser.parse_args()

tests/test1.py

@@ -0,0 +1,26 @@
+# File: tests/test_slack_data_loader.py
+
+import pytest
+from your_module import SlackDataLoader  
+import pandas as pd
+
+@pytest.fixture
+def slack_data_loader():
+    # Set up SlackDataLoader instance if needed
+    return SlackDataLoader()
+
+def test_load_data_columns(slack_data_loader):
+
+    expected_columns = ['col1', 'col2', 'col3']  
+    data_frame = slack_data_loader.load_data()  
+    assert isinstance(data_frame, pd.DataFrame)
+    assert all(column in data_frame.columns for column in expected_columns), "Columns do not match the expected columns"
+
+def test_process_data_columns(slack_data_loader):
+    expected_columns = ['processed_column1', 'processed_column2'] 
+
+    data_frame = slack_data_loader.load_data()  
+    processed_data_frame = slack_data_loader.process_data(data_frame)  
+
+    assert isinstance(processed_data_frame, pd.DataFrame)
+    assert all(column in processed_data_frame.columns for column in expected_columns), "Processed columns do not match the expected columns"