diff --git a/.gitignore b/.gitignore
index 8cd10b4..152d003 100644
--- a/.gitignore
+++ b/.gitignore
@@ -12,7 +12,7 @@ conf/**/*credentials*
 # ignore everything in the following folders
 data/**
 logs/**
-
+anonymized/**
 # except their sub-folders
 !data/**/
 !logs/**/
diff --git a/Text.txt.txt b/Text.txt.txt
new file mode 100644
index 0000000..150fce7
--- /dev/null
+++ b/Text.txt.txt
@@ -0,0 +1,10 @@
+My first text
+<<<<<<< HEAD
+Second Text
+=======
+Before submission
+30 minutes before submission
+>>>>>>> 8ab44a9c7bb8cdbc61971c3fa6ef7584546bbe2d
+First day training
+no one
+go
\ No newline at end of file
diff --git a/Untitled.ipynb b/Untitled.ipynb
new file mode 100644
index 0000000..f80e15c
--- /dev/null
+++ b/Untitled.ipynb
@@ -0,0 +1,92 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "1d795814-731b-4f8b-a4ec-82668183d083",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#Loading necessary packages\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import gensim\n",
+    "from gensim.models import CoherenceModel\n",
+    "from gensim import corpora\n",
+    "import pandas as pd\n",
+    "from pprint import pprint\n",
+    "import string\n",
+    "import os\n",
+    "import re"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2f935b8-9bf5-4715-9fcd-1c5907ea8848",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#data loader class\n",
+    "class DataLoader:\n",
+    "  def __init__(self,dir_name,file_name):\n",
+    "    self.dir_name=dir_name\n",
+    "    self.file_name = file_name\n",
+    "\n",
+    "\n",
+    "  def read_csv(self):\n",
+    "    os.chdir(self.dir_name)\n",
+    "    tweets_df=pd.read_csv(self.file_name)\n",
+    "    return tweets_df\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d5d2b3c-d207-4181-9843-260120eb29ea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#object creation\n",
+    "DataLoader_obj= DataLoader('drive/MyDrive','cleaned_fintech_data.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a81c803-f209-49cc-88bc-70c57b2abd5e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tweets_df=DataLoader_obj.read_csv()\n",
+    "tweets_df.dropna()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/parse_slack_data.ipynb b/notebooks/parse_slack_data.ipynb
index e3774f8..1caab9e 100644
--- a/notebooks/parse_slack_data.ipynb
+++ b/notebooks/parse_slack_data.ipynb
@@ -3,7 +3,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "%reload_ext autoreload\n",
@@ -13,7 +15,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "import os, sys\n",
@@ -28,17 +32,36 @@
     "import seaborn as sns\n",
     "\n",
     "from nltk.corpus import stopwords\n",
-    "from wordcloud import WordCloud"
+    "from wordcloud import WordCloud #installing wordcloud library\n",
+    "\n",
+    "import nltk\n",
+    "nltk.download('punkt')\n",
+    "from nltk.corpus import stopwords\n",
+    "from wordcloud import WordCloud\n",
+    "nltk.download('stopwords')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "!pip install wordcloud"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "# Add parent directory to path to import modules from src\n",
-    "rpath = os.path.abspath('..')\n",
+    "rpath = os.path.abspath(r'C:\\Users\\moyka\\OneDrive\\Documents\\GitHub\\week0_starter_network_analysis')\n",
     "if rpath not in sys.path:\n",
     "    sys.path.insert(0, rpath)\n",
     "\n",
@@ -98,7 +121,8 @@
     "    combined = []\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",
+    "            file_content = json.load(slack_data)\n",
+    "            combined.append(file_content)\n",
     "\n",
     "    # loop through all json files and extract required informations\n",
     "    dflist = []\n",
@@ -195,6 +219,43 @@
     "    return comm_dict"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "df = slack_parser(r'C:/Users/moyka/OneDrive/Documents/GitHub/allweeks89/')\n",
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "PSR = parse_slack_reaction(r'C:/Users/moyka/OneDrive/Documents/GitHub/allweeks89/', 'allweeks89')\n",
+    "PSR[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "result_data = parse_slack_reaction(r'C:/Users/moyka/OneDrive/Documents/GitHub/allweeks89/', 'allweeks89')\n",
+    "df = pd.DataFrame(result_data)\n",
+    "df.to_csv(r'C:\\Users\\moyka\\Desktop\\New\\file2.csv')"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -259,6 +320,30 @@
     "    return ac_comm_dict"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "converted_time = convert_2_timestamp('msg_sent_time', df)\n",
+    "converted_time[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "get_tagged_use = get_tagged_users(df)\n",
+    "get_tagged_use[:5]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -321,6 +406,19 @@
     "    plt.show()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "pfill = slack_parser(r'C:/Users/moyka/OneDrive/Documents/GitHub/allweeks89/')\n",
+    "pfill.info()\n",
+    "\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -336,7 +434,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# which user has the highest number of reply counts?"
+    "# which user has the highest number of reply counts?\n",
+    "#draw_avg_reply_users_count(pfill, channel='YourChannelName')\n",
+    "user_with_highest_replies = pfill.groupby('sender_name')['reply_count'].sum().idxmax()\n",
+    "print(f\"The user with the highest number of reply counts is: {user_with_highest_replies}\")"
    ]
   },
   {
@@ -345,7 +446,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Visualize reply counts per user per channel"
+    "# Visualize reply counts per user per channel\n",
+    "draw_avg_reply_users_count(pfill,'allweeks89')"
    ]
   },
   {
@@ -354,52 +456,117 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# what is the time range of the day that most messages are sent?\n"
+    "# what is the time range of the day that most messages are sent?\n",
+    "pfill['msg_sent_timestamp'] = utils.convert_2_timestamp('msg_sent_time', pfill)\n",
+    "pfill['hour'] = pd.to_datetime(pfill['msg_sent_timestamp']).dt.hour\n",
+    "\n",
+    "# Plot the histogram\n",
+    "sns.set(style=\"whitegrid\")\n",
+    "plt.figure(figsize=(12, 8))\n",
+    "sns.histplot(pfill['hour'], bins=24, kde=False)\n",
+    "plt.yscale('log')\n",
+    "plt.title('Message Counts by Hour of the Day')\n",
+    "plt.xlabel('Hour of the Day')\n",
+    "plt.ylabel('Message Count')\n",
+    "\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# what kind of messages are replied faster than others?"
+    "# what kind of messages are replied faster than others?\n",
+    "# Convert msg_sent_time and tm_thread_end to timestamps\n",
+    "pfill['msg_sent_timestamp'] = utils.convert_2_timestamp('msg_sent_time', pfill)\n",
+    "pfill['tm_thread_end_timestamp'] = utils.convert_2_timestamp('tm_thread_end', pfill)\n",
+    "\n",
+    "# Calculate the time it takes to receive a reply\n",
+    "pfill['reply_time'] = (pd.to_datetime(pfill['tm_thread_end_timestamp']) - pd.to_datetime(pfill['msg_sent_timestamp'])).dt.total_seconds()\n",
+    "\n",
+    "# Plotting\n",
+    "sns.set(style=\"whitegrid\")\n",
+    "plt.figure(figsize=(8, 6))\n",
+    "sns.boxplot(x='msg_dist_type', y='reply_time', data=pfill)\n",
+    "plt.yscale('log')\n",
+    "plt.title('Time to Receive Reply for Different Message Types')\n",
+    "plt.xlabel('Message Distribution Type')\n",
+    "plt.ylabel('Reply Time (seconds)')\n",
+    "plt.xticks(rotation=45, ha='right')\n",
+    "\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Relationship between # of messages and # of reactions"
+    "# Relationship between # of messages and # of reactions\n",
+    "grouped_data = pfill.groupby(['sender_name', 'channel'])['reply_count'].sum().reset_index()\n",
+    "\n",
+    "# Plotting\n",
+    "plt.figure(figsize=(12, 8))\n",
+    "sns.barplot(x='sender_name', y='reply_count', hue='channel', data=grouped_data)\n",
+    "plt.title('Reply Counts per User per Channel')\n",
+    "plt.xlabel('User')\n",
+    "plt.ylabel('Total Reply Counts')\n",
+    "plt.xticks(rotation=45, ha='right')\n",
+    "plt.legend(title='Channel', loc='upper right')\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Classify messages into different categories such as questions, answers, comments, etc."
+    "# Classify messages into different categories such as questions, answers, comments, etc.\n",
+    "# Get tagged users in the messages\n",
+    "pfill['tagged_users'] = get_tagged_users(pfill)\n",
+    "\n",
+    "# Create new columns for message categories\n",
+    "pfill['category'] = 'Other'  # Default category\n",
+    "\n",
+    "# Identify and classify messages based on certain keywords or patterns\n",
+    "pfill.loc[pfill['msg_content'].str.contains('(?:^|\\W)\\\\?+'), 'category'] = 'Question'\n",
+    "pfill.loc[pfill['msg_content'].str.contains('(?:^|\\W)answer(?:$|\\W)', case=False), 'category'] = 'Answer'\n",
+    "pfill.loc[pfill['msg_content'].str.contains('(?:^|\\W)comment(?:$|\\W)', case=False), 'category'] = 'Comment'\n",
+    "\n",
+    "# Display the distribution of message categories\n",
+    "category_counts = pfill['category'].value_counts()\n",
+    "print(category_counts)\n",
+    "\n",
+    "# Plot the distribution\n",
+    "category_counts.plot(kind='bar', figsize=(10, 6))\n",
+    "plt.title('Distribution of Message Categories')\n",
+    "plt.xlabel('Message Category')\n",
+    "plt.ylabel('Count')\n",
+    "plt.show()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Which users got the most reactions?"
+    "# Which users got the most reactions?\n",
+    "draw_user_reaction(pfill, channel='Random')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Model topics mentioned in the channel"
+    "# Model topics mentioned in the channel\n",
+    "draw_wordcloud(pfill['msg_content'], week='Random')"
    ]
   },
   {
@@ -408,7 +575,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# What are the topics that got the most reactions?"
+    "# What are the topics that got the most reactions?\n",
+    "\n",
+    "\n",
+    "# Parse Slack reactions for the 'allweeks89' channel\n",
+    "reaction_data = parse_slack_reaction(r'C:/Users/moyka/OneDrive/Documents/GitHub/allweeks89/', 'allweeks89')\n",
+    "\n",
+    "# Get the topics with the most reactions\n",
+    "top_reacted_topics = reaction_data.groupby('message')['reaction_count'].sum().sort_values(ascending=False)\n",
+    "\n",
+    "# Display the top topics with the most reactions\n",
+    "print(top_reacted_topics.head(10))"
    ]
   },
   {
@@ -430,7 +607,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -444,7 +621,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.11.5"
   }
  },
  "nbformat": 4,