From ec1bbfe128a9ceed37412c04ae1c7b626cddc31a Mon Sep 17 00:00:00 2001
From: Natnael Kibru <nathnaelkibru@gmail.com>
Date: Mon, 27 Nov 2023 21:21:45 +0300
Subject: [PATCH] final commit

---
 src/loader.py |  6 +++++-
 src/utils.py  | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/src/loader.py b/src/loader.py
index c75b68d..55d8b81 100644
--- a/src/loader.py
+++ b/src/loader.py
@@ -60,7 +60,11 @@ def get_channel_messages(self, channel_name):
         write a function to get all the messages from a channel
         
         '''
-
+        with open(os.path.join(self.path, "message.json"), 'r') as f:
+          messages = json.load(f)
+        
+        return messages[channel_name]
+       
     # 
     def get_user_map(self):
         '''
diff --git a/src/utils.py b/src/utils.py
index 45dda22..0b9ccc1 100644
--- a/src/utils.py
+++ b/src/utils.py
@@ -180,3 +180,43 @@ def convert_2_timestamp(column, data):
                 timestamp_.append(a.strftime('%Y-%m-%d %H:%M:%S'))
         return timestamp_
     else: print(f"{column} not in data")
+
+    def get_tagged_users(df):
+        """get all @ in the messages"""
+
+    return df['msg_content'].map(lambda x: re.findall(r'@U\w+', x))
+
+
+    
+def map_userid_2_realname(user_profile: dict, comm_dict: dict, plot=False):
+    """
+    map slack_id to realnames
+    user_profile: a dictionary that contains users info such as real_names
+    comm_dict: a dictionary that contains slack_id and total_message sent by that slack_id
+    """
+    user_dict = {} # to store the id
+    real_name = [] # to store the real name
+    ac_comm_dict = {} # to store the mapping
+    count = 0
+    # collect all the real names
+    for i in range(len(user_profile['profile'])):
+        real_name.append(dict(user_profile['profile'])[i]['real_name'])
+
+    # loop the slack ids
+    for i in user_profile['id']:
+        user_dict[i] = real_name[count]
+        count += 1
+
+    # to store mapping
+    for i in comm_dict:
+        if i in user_dict:
+            ac_comm_dict[user_dict[i]] = comm_dict[i]
+
+    ac_comm_dict = pd.DataFrame(data= zip(ac_comm_dict.keys(), ac_comm_dict.values()),
+    columns=['LearnerName', '# of Msg sent in Threads']).sort_values(by='# of Msg sent in Threads', ascending=False)
+    
+    if plot:
+        ac_comm_dict.plot.bar(figsize=(15, 7.5), x='LearnerName', y='# of Msg sent in Threads')
+        plt.title('Student based on Message sent in thread', size=20)
+        
+    return ac_comm_dict
\ No newline at end of file