diff --git "a/Reference files/Copy_Lab_5_hands_on_peer_review.ipynb" "b/Reference files/Copy_Lab_5_hands_on_peer_review.ipynb"
new file mode 100644--- /dev/null
+++ "b/Reference files/Copy_Lab_5_hands_on_peer_review.ipynb"
@@ -0,0 +1,1834 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# 🚀 Intro to ML and Linear Regression\n",
+        "\n",
+        "## 🎯 Real-Life Challenge: The Academic Publishing Crisis\n",
+        "Imagine you're the program chair for a prestigious AI conference. You've just received 5,000 paper submissions, and you need to:\n",
+        "\n",
+        "Decide which papers to accept (only 20% can be accepted)\n",
+        "Ensure fair and consistent reviews\n",
+        "Understand what makes reviewers confident in their assessments\n",
+        "\n",
+        "The Problem: Human reviewers are inconsistent. Some are harsh, others lenient. Some write detailed reviews, others just a few sentences. How can we use data to understand and improve this process?\n",
+        "\n",
+        "**Your Mission: Build a machine learning system to analyze review patterns and predict paper acceptance!**\n",
+        "\n",
+        "\n",
+        "---\n",
+        "\n",
+        "## 📚 What you will learn\n",
+        "Today's regression analysis is your first step into supervised learning - where we use labeled data (papers with known accept/reject decisions) to train models that can make predictions on new data.\n",
+        "\n",
+        "## Key Concepts You'll Master:\n",
+        "\n",
+        "1. **Linear Regression (线性回归):**\n",
+        "\n",
+        "Definition: A statistical method that models the relationship between a dependent variable and one or more independent variables by fitting a linear equation\n",
+        "\n",
+        "Real-world example: Predicting house prices based on size and location\n",
+        "\n",
+        "2. **Correlation Analysis (相关性分析):**\n",
+        "\n",
+        "Definition: Statistical measure that shows how strongly two variables are related\n",
+        "\n",
+        "Range: -1 (perfect negative correlation) to +1 (perfect positive correlation)\n",
+        "\n",
+        "\n",
+        "\n",
+        "3. **Reading Linear Regression Output (解读线性回归结果):**\n",
+        "\n",
+        "- R-squared (R²): Proportion of variance explained by the model (0-1)\n",
+        "- p-value: Probability that the observed relationship occurred by chance\n",
+        "- Coefficients (系数): How much the dependent variable changes with a one-unit change in the independent variable\n",
+        "- Standard errors: Uncertainty in coefficient estimates\n",
+        "- Confidence intervals: Range where true coefficient likely lies\n",
+        "\n",
+        "\n",
+        "**Building on Previous Knowledge:**\n",
+        "\n",
+        "We'll apply the data merging techniques you learned to combine multiple datasets\n",
+        "We'll use NLP tokenization skills to extract features from text\n",
+        "New focus: Using these processed features to build predictive models\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "M-0UhUz2J-Gd"
+      },
+      "id": "M-0UhUz2J-Gd"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# 🛠️ Step-by-Step Problem Solving Journey\n",
+        "## Step 1: Setting Up Your Data Science Toolkit\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "V0R-KlbINvnv"
+      },
+      "id": "V0R-KlbINvnv"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "da7c1aac",
+      "metadata": {
+        "id": "da7c1aac"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import pandas as pd\n",
+        "import scipy.stats as stats\n",
+        "import matplotlib.pyplot as plt\n",
+        "import sklearn\n",
+        "from nltk.tokenize import word_tokenize\n",
+        "\n",
+        "\n",
+        "import seaborn as sns\n",
+        "sns.set_style(\"whitegrid\")\n",
+        "sns.set_context(\"poster\")\n",
+        "\n",
+        "# special matplotlib argument for improved plots\n",
+        "from matplotlib import rcParams"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Knowledge Point: These libraries are the foundation of data science in Python:\n",
+        "\n",
+        "- pandas: Data manipulation (数据处理)\n",
+        "- matplotlib/seaborn: Visualization (数据可视化)\n",
+        "- nltk: Natural language processing (自然语言处理)\n",
+        "- statsmodels: Statistical modeling (统计建模)"
+      ],
+      "metadata": {
+        "id": "UK1RtbdiOBZ6"
+      },
+      "id": "UK1RtbdiOBZ6"
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 2: Loading and Understanding Your Data\n",
+        "\n",
+        "Before diving into analysis, always understand your data structure. What information do we have about each review? Each submission?\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "wF-dQ1BSOOpT"
+      },
+      "id": "wF-dQ1BSOOpT"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "54fe4107",
+      "metadata": {
+        "id": "54fe4107"
+      },
+      "outputs": [],
+      "source": [
+        "df_reviews = pd.read_csv('../data/reviews.csv')\n",
+        "df_submissions = pd.read_csv('../data/Submissions.csv')\n",
+        "df_dec = pd.read_csv('../data/decision.csv')\n",
+        "df_keyword = pd.read_csv('../data/submission_keyword.csv')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "89df00bb",
+      "metadata": {
+        "id": "89df00bb",
+        "outputId": "5181fe4f-5209-4a5d-8ebe-cfa2127789c2"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>rating_int</th>\n",
+              "      <th>confidence_int</th>\n",
+              "      <th>review</th>\n",
+              "      <th>forum</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>There is a lot of recent work on link-predicti...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>Pros:\\n\\n- The different attention techniques ...</td>\n",
+              "      <td>uKhGRvM8QNH</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>5</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>Overview of the paper: \\nThis paper studies th...</td>\n",
+              "      <td>IrM64DGB21</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>6</td>\n",
+              "      <td>3.0</td>\n",
+              "      <td>## Summary\\nThe authors propose a near minimax...</td>\n",
+              "      <td>ww-7bdU6GA9</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>The paper proposed a new method to prune a neu...</td>\n",
+              "      <td>j0uePNuoBho</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>25311</th>\n",
+              "      <td>8</td>\n",
+              "      <td>3.0</td>\n",
+              "      <td>This paper introduces a 'GPU-friendly' variant...</td>\n",
+              "      <td>r1VGvBcxl</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>25312</th>\n",
+              "      <td>3</td>\n",
+              "      <td>5.0</td>\n",
+              "      <td>This paper is relatively difficult to parse. M...</td>\n",
+              "      <td>rkFd2P5gl</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>25313</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>This paper is technically sound. It highlights...</td>\n",
+              "      <td>SyVVJ85lg</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>25314</th>\n",
+              "      <td>5</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>A few issues with this paper:\\n1- I find findi...</td>\n",
+              "      <td>Bygq-H9eg</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>25315</th>\n",
+              "      <td>8</td>\n",
+              "      <td>5.0</td>\n",
+              "      <td>This paper studies in depth the idea of quanti...</td>\n",
+              "      <td>S1_pAu9xl</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>25316 rows × 4 columns</p>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "       rating_int  confidence_int  \\\n",
+              "0               6             4.0   \n",
+              "1               6             4.0   \n",
+              "2               5             4.0   \n",
+              "3               6             3.0   \n",
+              "4               6             4.0   \n",
+              "...           ...             ...   \n",
+              "25311           8             3.0   \n",
+              "25312           3             5.0   \n",
+              "25313           6             4.0   \n",
+              "25314           5             4.0   \n",
+              "25315           8             5.0   \n",
+              "\n",
+              "                                                  review        forum  \n",
+              "0      There is a lot of recent work on link-predicti...  tGZu6DlbreV  \n",
+              "1      Pros:\\n\\n- The different attention techniques ...  uKhGRvM8QNH  \n",
+              "2      Overview of the paper: \\nThis paper studies th...   IrM64DGB21  \n",
+              "3      ## Summary\\nThe authors propose a near minimax...  ww-7bdU6GA9  \n",
+              "4      The paper proposed a new method to prune a neu...  j0uePNuoBho  \n",
+              "...                                                  ...          ...  \n",
+              "25311  This paper introduces a 'GPU-friendly' variant...    r1VGvBcxl  \n",
+              "25312  This paper is relatively difficult to parse. M...    rkFd2P5gl  \n",
+              "25313  This paper is technically sound. It highlights...    SyVVJ85lg  \n",
+              "25314  A few issues with this paper:\\n1- I find findi...    Bygq-H9eg  \n",
+              "25315  This paper studies in depth the idea of quanti...    S1_pAu9xl  \n",
+              "\n",
+              "[25316 rows x 4 columns]"
+            ]
+          },
+          "execution_count": 20,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_reviews[['rating_int','confidence_int','review','forum']]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "cb8f9a26",
+      "metadata": {
+        "id": "cb8f9a26",
+        "outputId": "0427c4b8-8ef5-49fa-ba33-db0bd785494e"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>abstract</th>\n",
+              "      <th>id</th>\n",
+              "      <th>conf_year</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>Stochastic optimization has become the workhor...</td>\n",
+              "      <td>r28GdiQF7vM</td>\n",
+              "      <td>2021</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>Graph neural networks (GNN) are powerful model...</td>\n",
+              "      <td>o29tNZZqGcN</td>\n",
+              "      <td>2021</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>Using a mix of shared and language-specific (L...</td>\n",
+              "      <td>Wj4ODo0uyCF</td>\n",
+              "      <td>2021</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>Latency of DNN (Deep Neural Network) based pre...</td>\n",
+              "      <td>_qJXkf347k</td>\n",
+              "      <td>2021</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>In the segmentation of fine-scale structures f...</td>\n",
+              "      <td>LGgdb4TS4Z</td>\n",
+              "      <td>2021</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7623</th>\n",
+              "      <td>In this paper, we propose and investigate a no...</td>\n",
+              "      <td>BkfiXiUlg</td>\n",
+              "      <td>2017</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7624</th>\n",
+              "      <td>We propose a learning method to quantify human...</td>\n",
+              "      <td>SkqMSCHxe</td>\n",
+              "      <td>2017</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7625</th>\n",
+              "      <td>Synthesizing high resolution photorealistic im...</td>\n",
+              "      <td>rJXTf9Bxg</td>\n",
+              "      <td>2017</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7626</th>\n",
+              "      <td>We ask whether neural networks can learn to us...</td>\n",
+              "      <td>S1HEBe_Jl</td>\n",
+              "      <td>2017</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7627</th>\n",
+              "      <td>Recurrent neural nets are widely used for pred...</td>\n",
+              "      <td>S1J0E-71l</td>\n",
+              "      <td>2017</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>7628 rows × 3 columns</p>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "                                               abstract           id  \\\n",
+              "0     Stochastic optimization has become the workhor...  r28GdiQF7vM   \n",
+              "1     Graph neural networks (GNN) are powerful model...  o29tNZZqGcN   \n",
+              "2     Using a mix of shared and language-specific (L...  Wj4ODo0uyCF   \n",
+              "3     Latency of DNN (Deep Neural Network) based pre...   _qJXkf347k   \n",
+              "4     In the segmentation of fine-scale structures f...   LGgdb4TS4Z   \n",
+              "...                                                 ...          ...   \n",
+              "7623  In this paper, we propose and investigate a no...    BkfiXiUlg   \n",
+              "7624  We propose a learning method to quantify human...    SkqMSCHxe   \n",
+              "7625  Synthesizing high resolution photorealistic im...    rJXTf9Bxg   \n",
+              "7626  We ask whether neural networks can learn to us...    S1HEBe_Jl   \n",
+              "7627  Recurrent neural nets are widely used for pred...    S1J0E-71l   \n",
+              "\n",
+              "      conf_year  \n",
+              "0          2021  \n",
+              "1          2021  \n",
+              "2          2021  \n",
+              "3          2021  \n",
+              "4          2021  \n",
+              "...         ...  \n",
+              "7623       2017  \n",
+              "7624       2017  \n",
+              "7625       2017  \n",
+              "7626       2017  \n",
+              "7627       2017  \n",
+              "\n",
+              "[7628 rows x 3 columns]"
+            ]
+          },
+          "execution_count": 21,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_submissions[['abstract','id','conf_year']]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 3: Data Integration - Connecting the Pieces\n",
+        "\n",
+        "Key Concept: Data Integration (数据集成) - The process of combining data from different sources. Here, we're linking reviews to their corresponding paper submissions using the forum and id fields as keys."
+      ],
+      "metadata": {
+        "id": "9tXNNKQaOgHp"
+      },
+      "id": "9tXNNKQaOgHp"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "7c0e5a23",
+      "metadata": {
+        "id": "7c0e5a23"
+      },
+      "outputs": [],
+      "source": [
+        "df_rs = pd.merge(df_reviews[['rating_int','confidence_int','review','forum']], df_submissions[['abstract','id','conf_year']], left_on='forum', right_on='id', how = 'inner')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 4: Text Preprocessing - Making Text Machine-Readable\n",
+        "\n",
+        "Key Concept: Tokenization (分词) - Breaking text into individual words or tokens. This allows us to:\n",
+        "\n",
+        "- Count words in reviews\n",
+        "- - Analyze text patterns\n",
+        "Create numerical features from text"
+      ],
+      "metadata": {
+        "id": "C7h2s0rjOvS5"
+      },
+      "id": "C7h2s0rjOvS5"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "3a8a8c83",
+      "metadata": {
+        "id": "3a8a8c83"
+      },
+      "outputs": [],
+      "source": [
+        "# Convert text to lowercase for consistency\n",
+        "df_rs['review'] = df_rs['review'].str.lower()\n",
+        "df_rs['abstract'] = df_rs['abstract'].str.lower()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "5c223b14",
+      "metadata": {
+        "id": "5c223b14"
+      },
+      "outputs": [],
+      "source": [
+        "# Tokenize reviews\n",
+        "df_rs['review_tokens'] = df_rs['review'].apply(word_tokenize)\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 5: Feature Engineering - Creating Meaningful Variables\n",
+        "\n",
+        "Key Concept: Feature Engineering (特征工程) - Creating new variables that better represent the underlying patterns. Here we create:\n",
+        "\n",
+        "- Average rating per paper\n",
+        "- Average review length\n",
+        "- verage reviewer confidence"
+      ],
+      "metadata": {
+        "id": "tfq_X8KxPdmH"
+      },
+      "id": "tfq_X8KxPdmH"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "39794625",
+      "metadata": {
+        "id": "39794625"
+      },
+      "outputs": [],
+      "source": [
+        "df_rs['review_num_tokens'] = df_rs['review_tokens'].apply(len)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "614a55b2",
+      "metadata": {
+        "id": "614a55b2"
+      },
+      "outputs": [],
+      "source": [
+        "df_rs_average = df_rs.groupby(['forum'])[['rating_int','review_num_tokens','confidence_int']].mean().reset_index()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 6: Exploratory Data Analysis - Finding Patterns\n",
+        "\n",
+        "Question: What pattern do you see? Do more confident reviewers tend to give higher or lower scores?"
+      ],
+      "metadata": {
+        "id": "XAhffKiWP1GQ"
+      },
+      "id": "XAhffKiWP1GQ"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "0e448fcf",
+      "metadata": {
+        "id": "0e448fcf",
+        "outputId": "87181896-dd6b-4bd4-e8dd-442ca0dfbcc9"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/var/folders/v9/8whxr3fd1mv_pwkjh0kn920m0000gn/T/ipykernel_32787/2078969568.py:3: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored\n",
+            "  scatter = plt.scatter(df_rs_average['confidence_int'], df_rs_average['rating_int'], alpha=0.6, cmap='viridis', edgecolor='w', linewidth=0.5)\n"
+          ]
+        },
+        {
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 1000x600 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Visualize the relationship between confidence and rating\n",
+        "\n",
+        "# Create a scatter plot\n",
+        "plt.figure(figsize=(10, 6))\n",
+        "scatter = plt.scatter(df_rs_average['confidence_int'], df_rs_average['rating_int'], alpha=0.6, cmap='viridis', edgecolor='w', linewidth=0.5)\n",
+        "\n",
+        "\n",
+        "# Add titles and labels\n",
+        "plt.title('Average Review Rating by Reviewer Confidence')\n",
+        "plt.xlabel('Reviewer Confidence')\n",
+        "plt.ylabel('Rating')\n",
+        "\n",
+        "# Customize ticks\n",
+        "plt.xticks(fontsize=12, rotation=45)\n",
+        "plt.yticks(fontsize=12)\n",
+        "\n",
+        "# Add grid\n",
+        "plt.grid(True, linestyle='--', alpha=0.7)\n",
+        "\n",
+        "\n",
+        "# Show plot\n",
+        "plt.tight_layout()\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "**Key Concept:** Linear Regression (线性回归) - A statistical method to model the relationship between variables. The red line shows the \"best fit\" that minimizes prediction errors."
+      ],
+      "metadata": {
+        "id": "_MxdqDK7RF2_"
+      },
+      "id": "_MxdqDK7RF2_"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "ab827b24",
+      "metadata": {
+        "id": "ab827b24",
+        "outputId": "839b8c43-997c-4793-a521-237d3effa036"
+      },
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 1000x600 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Create a regression plot with trend line\n",
+        "\n",
+        "# Set the aesthetic style of the plots\n",
+        "sns.set(style=\"whitegrid\")\n",
+        "\n",
+        "# Create a regression plot\n",
+        "plt.figure(figsize=(10, 6))\n",
+        "sns.regplot(y=\"rating_int\", x=\"confidence_int\", data=df_rs_average, fit_reg=True,\n",
+        "            scatter_kws={'s': 50, 'alpha': 0.6, 'color': 'b'},\n",
+        "            line_kws={'color': 'red', 'linewidth': 2})\n",
+        "\n",
+        "# Customize the plot with titles and labels\n",
+        "plt.title('Title', fontsize=20)\n",
+        "#plt.xlabel('confidence_int', fontsize=15)\n",
+        "#plt.ylabel('rating_int', fontsize=15)\n",
+        "\n",
+        "# Customize the ticks on the axes\n",
+        "plt.xticks(fontsize=12)\n",
+        "plt.yticks(fontsize=12)\n",
+        "\n",
+        "# Show grid\n",
+        "plt.grid(True, linestyle='--', alpha=0.7)\n",
+        "\n",
+        "# Show the plot\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Step 7: Statistical Modeling - Getting Measurements\n",
+        "\n",
+        "**Interpretation Guide:**\n",
+        "\n",
+        "- R-squared: How well the model explains the data (0-1, higher is better)\n",
+        "- p-value: Statistical significance (< 0.05 means the relationship is likely real)\n",
+        "- Coefficient: How much Y changes when X increases by 1"
+      ],
+      "metadata": {
+        "id": "8uvp0twrRP7b"
+      },
+      "id": "8uvp0twrRP7b"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "977ee019",
+      "metadata": {
+        "id": "977ee019",
+        "outputId": "cdda5ee2-ec6c-470e-ee58-c4b11de04f31"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n",
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n",
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n"
+          ]
+        },
+        {
+          "data": {
+            "text/html": [
+              "<table class=\"simpletable\">\n",
+              "<caption>OLS Regression Results</caption>\n",
+              "<tr>\n",
+              "  <th>Dep. Variable:</th>       <td>rating_int</td>    <th>  R-squared:         </th> <td>   0.028</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.028</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   153.8</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Date:</th>             <td>Tue, 02 Jul 2024</td> <th>  Prob (F-statistic):</th> <td>7.76e-35</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Time:</th>                 <td>21:11:32</td>     <th>  Log-Likelihood:    </th> <td> -8181.6</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>No. Observations:</th>      <td>  5379</td>      <th>  AIC:               </th> <td>1.637e+04</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Df Residuals:</th>          <td>  5377</td>      <th>  BIC:               </th> <td>1.638e+04</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>    \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
+              "</tr>\n",
+              "</table>\n",
+              "<table class=\"simpletable\">\n",
+              "<tr>\n",
+              "         <td></td>           <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Intercept</th>      <td>    6.8855</td> <td>    0.113</td> <td>   60.819</td> <td> 0.000</td> <td>    6.664</td> <td>    7.107</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>confidence_int</th> <td>   -0.3713</td> <td>    0.030</td> <td>  -12.400</td> <td> 0.000</td> <td>   -0.430</td> <td>   -0.313</td>\n",
+              "</tr>\n",
+              "</table>\n",
+              "<table class=\"simpletable\">\n",
+              "<tr>\n",
+              "  <th>Omnibus:</th>       <td>16.185</td> <th>  Durbin-Watson:     </th> <td>   1.963</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td>  13.384</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Skew:</th>          <td>-0.048</td> <th>  Prob(JB):          </th> <td> 0.00124</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Kurtosis:</th>      <td> 2.775</td> <th>  Cond. No.          </th> <td>    30.3</td>\n",
+              "</tr>\n",
+              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
+            ],
+            "text/plain": [
+              "<class 'statsmodels.iolib.summary.Summary'>\n",
+              "\"\"\"\n",
+              "                            OLS Regression Results                            \n",
+              "==============================================================================\n",
+              "Dep. Variable:             rating_int   R-squared:                       0.028\n",
+              "Model:                            OLS   Adj. R-squared:                  0.028\n",
+              "Method:                 Least Squares   F-statistic:                     153.8\n",
+              "Date:                Tue, 02 Jul 2024   Prob (F-statistic):           7.76e-35\n",
+              "Time:                        21:11:32   Log-Likelihood:                -8181.6\n",
+              "No. Observations:                5379   AIC:                         1.637e+04\n",
+              "Df Residuals:                    5377   BIC:                         1.638e+04\n",
+              "Df Model:                           1                                         \n",
+              "Covariance Type:            nonrobust                                         \n",
+              "==================================================================================\n",
+              "                     coef    std err          t      P>|t|      [0.025      0.975]\n",
+              "----------------------------------------------------------------------------------\n",
+              "Intercept          6.8855      0.113     60.819      0.000       6.664       7.107\n",
+              "confidence_int    -0.3713      0.030    -12.400      0.000      -0.430      -0.313\n",
+              "==============================================================================\n",
+              "Omnibus:                       16.185   Durbin-Watson:                   1.963\n",
+              "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               13.384\n",
+              "Skew:                          -0.048   Prob(JB):                      0.00124\n",
+              "Kurtosis:                       2.775   Cond. No.                         30.3\n",
+              "==============================================================================\n",
+              "\n",
+              "Notes:\n",
+              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+              "\"\"\""
+            ]
+          },
+          "execution_count": 29,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "import statsmodels.api as sm\n",
+        "from statsmodels.formula.api import ols\n",
+        "\n",
+        "# Simple linear regression\n",
+        "m = ols('rating_int ~ confidence_int',df_rs_average).fit()\n",
+        "m.summary()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "fe44fcf1",
+      "metadata": {
+        "id": "fe44fcf1",
+        "outputId": "5740ebca-6ce9-486a-8685-824cf22edf2d"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "Index(['forum', 'rating_int', 'review_num_tokens', 'confidence_int'], dtype='object')"
+            ]
+          },
+          "execution_count": 30,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_rs_average.columns"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "23d96627",
+      "metadata": {
+        "id": "23d96627",
+        "outputId": "631a8457-03f7-4ffe-8f00-7549eb1b1edd"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n",
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n",
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n",
+            "/opt/anaconda3/envs/nlp/lib/python3.10/site-packages/patsy/util.py:672: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead\n",
+            "  return _pandas_is_categorical_dtype(dt)\n"
+          ]
+        },
+        {
+          "data": {
+            "text/html": [
+              "<table class=\"simpletable\">\n",
+              "<caption>OLS Regression Results</caption>\n",
+              "<tr>\n",
+              "  <th>Dep. Variable:</th>       <td>rating_int</td>    <th>  R-squared:         </th> <td>   0.028</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.027</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   76.90</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Date:</th>             <td>Tue, 02 Jul 2024</td> <th>  Prob (F-statistic):</th> <td>1.18e-33</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Time:</th>                 <td>21:11:33</td>     <th>  Log-Likelihood:    </th> <td> -8181.6</td> \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>No. Observations:</th>      <td>  5379</td>      <th>  AIC:               </th> <td>1.637e+04</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Df Residuals:</th>          <td>  5376</td>      <th>  BIC:               </th> <td>1.639e+04</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Df Model:</th>              <td>     2</td>      <th>                     </th>     <td> </td>    \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
+              "</tr>\n",
+              "</table>\n",
+              "<table class=\"simpletable\">\n",
+              "<tr>\n",
+              "          <td></td>             <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Intercept</th>         <td>    6.8924</td> <td>    0.117</td> <td>   58.929</td> <td> 0.000</td> <td>    6.663</td> <td>    7.122</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>review_num_tokens</th> <td>-1.842e-05</td> <td> 7.73e-05</td> <td>   -0.238</td> <td> 0.812</td> <td>   -0.000</td> <td>    0.000</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>confidence_int</th>    <td>   -0.3708</td> <td>    0.030</td> <td>  -12.340</td> <td> 0.000</td> <td>   -0.430</td> <td>   -0.312</td>\n",
+              "</tr>\n",
+              "</table>\n",
+              "<table class=\"simpletable\">\n",
+              "<tr>\n",
+              "  <th>Omnibus:</th>       <td>16.217</td> <th>  Durbin-Watson:     </th> <td>   1.963</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td>  13.437</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Skew:</th>          <td>-0.049</td> <th>  Prob(JB):          </th> <td> 0.00121</td>\n",
+              "</tr>\n",
+              "<tr>\n",
+              "  <th>Kurtosis:</th>      <td> 2.775</td> <th>  Cond. No.          </th> <td>4.26e+03</td>\n",
+              "</tr>\n",
+              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 4.26e+03. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
+            ],
+            "text/plain": [
+              "<class 'statsmodels.iolib.summary.Summary'>\n",
+              "\"\"\"\n",
+              "                            OLS Regression Results                            \n",
+              "==============================================================================\n",
+              "Dep. Variable:             rating_int   R-squared:                       0.028\n",
+              "Model:                            OLS   Adj. R-squared:                  0.027\n",
+              "Method:                 Least Squares   F-statistic:                     76.90\n",
+              "Date:                Tue, 02 Jul 2024   Prob (F-statistic):           1.18e-33\n",
+              "Time:                        21:11:33   Log-Likelihood:                -8181.6\n",
+              "No. Observations:                5379   AIC:                         1.637e+04\n",
+              "Df Residuals:                    5376   BIC:                         1.639e+04\n",
+              "Df Model:                           2                                         \n",
+              "Covariance Type:            nonrobust                                         \n",
+              "=====================================================================================\n",
+              "                        coef    std err          t      P>|t|      [0.025      0.975]\n",
+              "-------------------------------------------------------------------------------------\n",
+              "Intercept             6.8924      0.117     58.929      0.000       6.663       7.122\n",
+              "review_num_tokens -1.842e-05   7.73e-05     -0.238      0.812      -0.000       0.000\n",
+              "confidence_int       -0.3708      0.030    -12.340      0.000      -0.430      -0.312\n",
+              "==============================================================================\n",
+              "Omnibus:                       16.217   Durbin-Watson:                   1.963\n",
+              "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               13.437\n",
+              "Skew:                          -0.049   Prob(JB):                      0.00121\n",
+              "Kurtosis:                       2.775   Cond. No.                     4.26e+03\n",
+              "==============================================================================\n",
+              "\n",
+              "Notes:\n",
+              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
+              "[2] The condition number is large, 4.26e+03. This might indicate that there are\n",
+              "strong multicollinearity or other numerical problems.\n",
+              "\"\"\""
+            ]
+          },
+          "execution_count": 31,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# Multiple regression with review length\n",
+        "m = ols('rating_int ~ review_num_tokens + confidence_int',df_rs_average).fit()\n",
+        "m.summary()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# 🎯 Practice Challenges"
+      ],
+      "metadata": {
+        "id": "iufVYLySR2RK"
+      },
+      "id": "iufVYLySR2RK"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "3099adfa",
+      "metadata": {
+        "id": "3099adfa",
+        "outputId": "5109e1fd-cfe5-4e1c-f618-9c738b6cc420"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>id</th>\n",
+              "      <th>tcdate</th>\n",
+              "      <th>tmdate</th>\n",
+              "      <th>number</th>\n",
+              "      <th>forum</th>\n",
+              "      <th>replyto</th>\n",
+              "      <th>title</th>\n",
+              "      <th>decision</th>\n",
+              "      <th>comment</th>\n",
+              "      <th>conf_name</th>\n",
+              "      <th>confidence</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>0zV62G_Z4s</td>\n",
+              "      <td>1610040357457</td>\n",
+              "      <td>1611063503220</td>\n",
+              "      <td>1</td>\n",
+              "      <td>meG3o0ttiAD</td>\n",
+              "      <td>meG3o0ttiAD</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>This paper introduces two new quantum neural n...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>SZvFCZvTsoS</td>\n",
+              "      <td>1610040498377</td>\n",
+              "      <td>1610992686336</td>\n",
+              "      <td>1</td>\n",
+              "      <td>AJY3fGPF1DC</td>\n",
+              "      <td>AJY3fGPF1DC</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>This paper considers the problem of identifica...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>-9zBJ8kapV</td>\n",
+              "      <td>1610040388799</td>\n",
+              "      <td>1610734729796</td>\n",
+              "      <td>1</td>\n",
+              "      <td>_O9YLet0wvN</td>\n",
+              "      <td>_O9YLet0wvN</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>The reviewers have ranked this paper as border...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>dswNkjMSvK</td>\n",
+              "      <td>1610040389095</td>\n",
+              "      <td>1610717627789</td>\n",
+              "      <td>1</td>\n",
+              "      <td>WoLQsYU8aZ</td>\n",
+              "      <td>WoLQsYU8aZ</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>This paper represents the PettingZoo library o...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>hHfc3BD1vIb</td>\n",
+              "      <td>1610040488610</td>\n",
+              "      <td>1610618696830</td>\n",
+              "      <td>1</td>\n",
+              "      <td>Sc8cY4Jpi3s</td>\n",
+              "      <td>Sc8cY4Jpi3s</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>Dear authors,\\n\\nI like to topic of your paper...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>10300</th>\n",
+              "      <td>iCMbtNSRp3s</td>\n",
+              "      <td>1642696832494</td>\n",
+              "      <td>1642696832494</td>\n",
+              "      <td>1</td>\n",
+              "      <td>j-63FSNcO5a</td>\n",
+              "      <td>j-63FSNcO5a</td>\n",
+              "      <td>Paper Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>The paper proposes a framework, named Disentag...</td>\n",
+              "      <td>ICLR2022</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>10301</th>\n",
+              "      <td>ZjiBIEPyMOn</td>\n",
+              "      <td>1642696832492</td>\n",
+              "      <td>1642696832492</td>\n",
+              "      <td>1</td>\n",
+              "      <td>AjGC97Aofee</td>\n",
+              "      <td>AjGC97Aofee</td>\n",
+              "      <td>Paper Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>This paper receives positive reviews. The auth...</td>\n",
+              "      <td>ICLR2022</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>10302</th>\n",
+              "      <td>-bEai7YVHEi</td>\n",
+              "      <td>1642696832460</td>\n",
+              "      <td>1642696832460</td>\n",
+              "      <td>1</td>\n",
+              "      <td>BnQhMqDfcKG</td>\n",
+              "      <td>BnQhMqDfcKG</td>\n",
+              "      <td>Paper Decision</td>\n",
+              "      <td>Accept (Spotlight)</td>\n",
+              "      <td>This paper introduced a probabilistic extensio...</td>\n",
+              "      <td>ICLR2022</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>10303</th>\n",
+              "      <td>RKQzOhYsYd5</td>\n",
+              "      <td>1642696832458</td>\n",
+              "      <td>1642696832458</td>\n",
+              "      <td>1</td>\n",
+              "      <td>JLbXkHkLCG6</td>\n",
+              "      <td>JLbXkHkLCG6</td>\n",
+              "      <td>Paper Decision</td>\n",
+              "      <td>Reject</td>\n",
+              "      <td>Learning policies from video demonstrations al...</td>\n",
+              "      <td>ICLR2022</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>10304</th>\n",
+              "      <td>xBFxR-EPLhR</td>\n",
+              "      <td>1642696832456</td>\n",
+              "      <td>1642696832456</td>\n",
+              "      <td>1</td>\n",
+              "      <td>7l1IjZVddDW</td>\n",
+              "      <td>7l1IjZVddDW</td>\n",
+              "      <td>Paper Decision</td>\n",
+              "      <td>Accept (Spotlight)</td>\n",
+              "      <td>This paper received 4 quality reviews. The reb...</td>\n",
+              "      <td>ICLR2022</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>10305 rows × 11 columns</p>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "                id         tcdate         tmdate  number        forum  \\\n",
+              "0       0zV62G_Z4s  1610040357457  1611063503220       1  meG3o0ttiAD   \n",
+              "1      SZvFCZvTsoS  1610040498377  1610992686336       1  AJY3fGPF1DC   \n",
+              "2       -9zBJ8kapV  1610040388799  1610734729796       1  _O9YLet0wvN   \n",
+              "3       dswNkjMSvK  1610040389095  1610717627789       1   WoLQsYU8aZ   \n",
+              "4      hHfc3BD1vIb  1610040488610  1610618696830       1  Sc8cY4Jpi3s   \n",
+              "...            ...            ...            ...     ...          ...   \n",
+              "10300  iCMbtNSRp3s  1642696832494  1642696832494       1  j-63FSNcO5a   \n",
+              "10301  ZjiBIEPyMOn  1642696832492  1642696832492       1  AjGC97Aofee   \n",
+              "10302  -bEai7YVHEi  1642696832460  1642696832460       1  BnQhMqDfcKG   \n",
+              "10303  RKQzOhYsYd5  1642696832458  1642696832458       1  JLbXkHkLCG6   \n",
+              "10304  xBFxR-EPLhR  1642696832456  1642696832456       1  7l1IjZVddDW   \n",
+              "\n",
+              "           replyto           title            decision  \\\n",
+              "0      meG3o0ttiAD  Final Decision              Reject   \n",
+              "1      AJY3fGPF1DC  Final Decision              Reject   \n",
+              "2      _O9YLet0wvN  Final Decision              Reject   \n",
+              "3       WoLQsYU8aZ  Final Decision              Reject   \n",
+              "4      Sc8cY4Jpi3s  Final Decision              Reject   \n",
+              "...            ...             ...                 ...   \n",
+              "10300  j-63FSNcO5a  Paper Decision     Accept (Poster)   \n",
+              "10301  AjGC97Aofee  Paper Decision     Accept (Poster)   \n",
+              "10302  BnQhMqDfcKG  Paper Decision  Accept (Spotlight)   \n",
+              "10303  JLbXkHkLCG6  Paper Decision              Reject   \n",
+              "10304  7l1IjZVddDW  Paper Decision  Accept (Spotlight)   \n",
+              "\n",
+              "                                                 comment conf_name confidence  \n",
+              "0      This paper introduces two new quantum neural n...  ICLR2021        NaN  \n",
+              "1      This paper considers the problem of identifica...  ICLR2021        NaN  \n",
+              "2      The reviewers have ranked this paper as border...  ICLR2021        NaN  \n",
+              "3      This paper represents the PettingZoo library o...  ICLR2021        NaN  \n",
+              "4      Dear authors,\\n\\nI like to topic of your paper...  ICLR2021        NaN  \n",
+              "...                                                  ...       ...        ...  \n",
+              "10300  The paper proposes a framework, named Disentag...  ICLR2022        NaN  \n",
+              "10301  This paper receives positive reviews. The auth...  ICLR2022        NaN  \n",
+              "10302  This paper introduced a probabilistic extensio...  ICLR2022        NaN  \n",
+              "10303  Learning policies from video demonstrations al...  ICLR2022        NaN  \n",
+              "10304  This paper received 4 quality reviews. The reb...  ICLR2022        NaN  \n",
+              "\n",
+              "[10305 rows x 11 columns]"
+            ]
+          },
+          "execution_count": 32,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_dec"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "56ae0b2f",
+      "metadata": {
+        "id": "56ae0b2f"
+      },
+      "outputs": [],
+      "source": [
+        "df_combined_model = pd.merge(df_rs, df_dec, left_on='forum', right_on='forum', how = 'inner')\n",
+        "\n",
+        "df_combined_model.to_csv('df_combined_model.csv')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "306e05ed",
+      "metadata": {
+        "id": "306e05ed",
+        "outputId": "4bdc1805-0234-4785-fbd8-3fe77ba9ccf8"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>rating_int</th>\n",
+              "      <th>confidence_int</th>\n",
+              "      <th>review</th>\n",
+              "      <th>forum</th>\n",
+              "      <th>abstract</th>\n",
+              "      <th>id_x</th>\n",
+              "      <th>conf_year</th>\n",
+              "      <th>review_tokens</th>\n",
+              "      <th>review_num_tokens</th>\n",
+              "      <th>id_y</th>\n",
+              "      <th>tcdate</th>\n",
+              "      <th>tmdate</th>\n",
+              "      <th>number</th>\n",
+              "      <th>replyto</th>\n",
+              "      <th>title</th>\n",
+              "      <th>decision</th>\n",
+              "      <th>comment</th>\n",
+              "      <th>conf_name</th>\n",
+              "      <th>confidence</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>there is a lot of recent work on link-predicti...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>this paper studies learning logic rules for re...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>2021</td>\n",
+              "      <td>[there, is, a, lot, of, recent, work, on, link...</td>\n",
+              "      <td>1537</td>\n",
+              "      <td>uVb3Ow-12JH</td>\n",
+              "      <td>1610045694102</td>\n",
+              "      <td>1610474017438</td>\n",
+              "      <td>1</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>There is a consensus among the reviewers that ...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>7</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>in this paper, the author proposes rnnlogic fo...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>this paper studies learning logic rules for re...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>2021</td>\n",
+              "      <td>[in, this, paper, ,, the, author, proposes, rn...</td>\n",
+              "      <td>722</td>\n",
+              "      <td>uVb3Ow-12JH</td>\n",
+              "      <td>1610045694102</td>\n",
+              "      <td>1610474017438</td>\n",
+              "      <td>1</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>There is a consensus among the reviewers that ...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>6</td>\n",
+              "      <td>2.0</td>\n",
+              "      <td>this paper focuses on learning logic rules via...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>this paper studies learning logic rules for re...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>2021</td>\n",
+              "      <td>[this, paper, focuses, on, learning, logic, ru...</td>\n",
+              "      <td>236</td>\n",
+              "      <td>uVb3Ow-12JH</td>\n",
+              "      <td>1610045694102</td>\n",
+              "      <td>1610474017438</td>\n",
+              "      <td>1</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>There is a consensus among the reviewers that ...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>8</td>\n",
+              "      <td>1.0</td>\n",
+              "      <td>in this work, the authors illustrate an approa...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>this paper studies learning logic rules for re...</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>2021</td>\n",
+              "      <td>[in, this, work, ,, the, authors, illustrate, ...</td>\n",
+              "      <td>121</td>\n",
+              "      <td>uVb3Ow-12JH</td>\n",
+              "      <td>1610045694102</td>\n",
+              "      <td>1610474017438</td>\n",
+              "      <td>1</td>\n",
+              "      <td>tGZu6DlbreV</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>There is a consensus among the reviewers that ...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>6</td>\n",
+              "      <td>4.0</td>\n",
+              "      <td>pros:\\n\\n- the different attention techniques ...</td>\n",
+              "      <td>uKhGRvM8QNH</td>\n",
+              "      <td>knowledge distillation, in which a student mod...</td>\n",
+              "      <td>uKhGRvM8QNH</td>\n",
+              "      <td>2021</td>\n",
+              "      <td>[pros, :, -, the, different, attention, techni...</td>\n",
+              "      <td>338</td>\n",
+              "      <td>a8RiFt2IlY</td>\n",
+              "      <td>1610040503192</td>\n",
+              "      <td>1610474110215</td>\n",
+              "      <td>1</td>\n",
+              "      <td>uKhGRvM8QNH</td>\n",
+              "      <td>Final Decision</td>\n",
+              "      <td>Accept (Poster)</td>\n",
+              "      <td>After the rebuttal stage, all reviewers lean p...</td>\n",
+              "      <td>ICLR2021</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "   rating_int  confidence_int  \\\n",
+              "0           6             4.0   \n",
+              "1           7             4.0   \n",
+              "2           6             2.0   \n",
+              "3           8             1.0   \n",
+              "4           6             4.0   \n",
+              "\n",
+              "                                              review        forum  \\\n",
+              "0  there is a lot of recent work on link-predicti...  tGZu6DlbreV   \n",
+              "1  in this paper, the author proposes rnnlogic fo...  tGZu6DlbreV   \n",
+              "2  this paper focuses on learning logic rules via...  tGZu6DlbreV   \n",
+              "3  in this work, the authors illustrate an approa...  tGZu6DlbreV   \n",
+              "4  pros:\\n\\n- the different attention techniques ...  uKhGRvM8QNH   \n",
+              "\n",
+              "                                            abstract         id_x  conf_year  \\\n",
+              "0  this paper studies learning logic rules for re...  tGZu6DlbreV       2021   \n",
+              "1  this paper studies learning logic rules for re...  tGZu6DlbreV       2021   \n",
+              "2  this paper studies learning logic rules for re...  tGZu6DlbreV       2021   \n",
+              "3  this paper studies learning logic rules for re...  tGZu6DlbreV       2021   \n",
+              "4  knowledge distillation, in which a student mod...  uKhGRvM8QNH       2021   \n",
+              "\n",
+              "                                       review_tokens  review_num_tokens  \\\n",
+              "0  [there, is, a, lot, of, recent, work, on, link...               1537   \n",
+              "1  [in, this, paper, ,, the, author, proposes, rn...                722   \n",
+              "2  [this, paper, focuses, on, learning, logic, ru...                236   \n",
+              "3  [in, this, work, ,, the, authors, illustrate, ...                121   \n",
+              "4  [pros, :, -, the, different, attention, techni...                338   \n",
+              "\n",
+              "          id_y         tcdate         tmdate  number      replyto  \\\n",
+              "0  uVb3Ow-12JH  1610045694102  1610474017438       1  tGZu6DlbreV   \n",
+              "1  uVb3Ow-12JH  1610045694102  1610474017438       1  tGZu6DlbreV   \n",
+              "2  uVb3Ow-12JH  1610045694102  1610474017438       1  tGZu6DlbreV   \n",
+              "3  uVb3Ow-12JH  1610045694102  1610474017438       1  tGZu6DlbreV   \n",
+              "4   a8RiFt2IlY  1610040503192  1610474110215       1  uKhGRvM8QNH   \n",
+              "\n",
+              "            title         decision  \\\n",
+              "0  Final Decision  Accept (Poster)   \n",
+              "1  Final Decision  Accept (Poster)   \n",
+              "2  Final Decision  Accept (Poster)   \n",
+              "3  Final Decision  Accept (Poster)   \n",
+              "4  Final Decision  Accept (Poster)   \n",
+              "\n",
+              "                                             comment conf_name confidence  \n",
+              "0  There is a consensus among the reviewers that ...  ICLR2021        NaN  \n",
+              "1  There is a consensus among the reviewers that ...  ICLR2021        NaN  \n",
+              "2  There is a consensus among the reviewers that ...  ICLR2021        NaN  \n",
+              "3  There is a consensus among the reviewers that ...  ICLR2021        NaN  \n",
+              "4  After the rebuttal stage, all reviewers lean p...  ICLR2021        NaN  "
+            ]
+          },
+          "execution_count": 32,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_combined_model"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "38e981ba",
+      "metadata": {
+        "id": "38e981ba"
+      },
+      "source": [
+        "1) Do the tokenization for both abstract and review including removing the stop words\n",
+        "\n",
+        "2) Run an analysis on what relationship we would like to analyze with linear regression given the features we have built\n",
+        "\n",
+        "3) Run the regression and interpret the results"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "43febdb7",
+      "metadata": {
+        "id": "43febdb7"
+      },
+      "source": [
+        "# Potential Relationships:\n",
+        "\n",
+        "1) Reviewer score and Review Confidence\n",
+        "2) Review Length and Review Score\n",
+        "3) Review Length and Review Confidence\n",
+        "\n",
+        "3) Review score + Conference Year ~ Accept/Reject\n",
+        "4) Conference Year ~ Review Confidence\n",
+        "\n",
+        "# Classification Relationships:\n",
+        "\n",
+        "6) Accept/Reject ~ Review Score + Conference Year + Reviewer Confidence + Submission Length + Topic"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [],
+      "metadata": {
+        "id": "L9Vhv31OJ8NJ"
+      },
+      "id": "L9Vhv31OJ8NJ"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "38a43bf4",
+      "metadata": {
+        "id": "38a43bf4",
+        "outputId": "64e5e843-daef-4149-a411-edd2a11a8c06"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>submission_id</th>\n",
+              "      <th>primary_keyword</th>\n",
+              "      <th>secondary_keyword</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>--gvHfE3Xf5</td>\n",
+              "      <td>reinforcement learning</td>\n",
+              "      <td>meta-learning</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>--rcOeCKRh</td>\n",
+              "      <td>transfer learning</td>\n",
+              "      <td>object detection</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>-0LuSWi6j4</td>\n",
+              "      <td>variational autoencoder</td>\n",
+              "      <td>deep generative models</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>-29uFS4FiDZ</td>\n",
+              "      <td>word embeddings</td>\n",
+              "      <td>other</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>-2FCwDKRREu</td>\n",
+              "      <td>representation learning</td>\n",
+              "      <td>other</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>...</th>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "      <td>...</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7635</th>\n",
+              "      <td>ztMLindFLWR</td>\n",
+              "      <td>graph neural networks</td>\n",
+              "      <td>graph representation learning</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7636</th>\n",
+              "      <td>zuDmDfeoB_1</td>\n",
+              "      <td>meta-learning</td>\n",
+              "      <td>other</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7637</th>\n",
+              "      <td>zv-typ1gPxA</td>\n",
+              "      <td>graph neural networks</td>\n",
+              "      <td>other</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7638</th>\n",
+              "      <td>zxEfpcmTDnF</td>\n",
+              "      <td>representation learning</td>\n",
+              "      <td>deep generative models</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>7639</th>\n",
+              "      <td>zz9hXVhf40</td>\n",
+              "      <td>model-based reinforcement learning</td>\n",
+              "      <td>offline reinforcement learning</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "<p>7640 rows × 3 columns</p>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "     submission_id                     primary_keyword  \\\n",
+              "0      --gvHfE3Xf5              reinforcement learning   \n",
+              "1       --rcOeCKRh                   transfer learning   \n",
+              "2       -0LuSWi6j4             variational autoencoder   \n",
+              "3      -29uFS4FiDZ                     word embeddings   \n",
+              "4      -2FCwDKRREu             representation learning   \n",
+              "...            ...                                 ...   \n",
+              "7635   ztMLindFLWR               graph neural networks   \n",
+              "7636   zuDmDfeoB_1                       meta-learning   \n",
+              "7637   zv-typ1gPxA               graph neural networks   \n",
+              "7638   zxEfpcmTDnF             representation learning   \n",
+              "7639    zz9hXVhf40  model-based reinforcement learning   \n",
+              "\n",
+              "                   secondary_keyword  \n",
+              "0                      meta-learning  \n",
+              "1                   object detection  \n",
+              "2             deep generative models  \n",
+              "3                              other  \n",
+              "4                              other  \n",
+              "...                              ...  \n",
+              "7635   graph representation learning  \n",
+              "7636                           other  \n",
+              "7637                           other  \n",
+              "7638          deep generative models  \n",
+              "7639  offline reinforcement learning  \n",
+              "\n",
+              "[7640 rows x 3 columns]"
+            ]
+          },
+          "execution_count": 33,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_keyword"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "0e9bce1e",
+      "metadata": {
+        "id": "0e9bce1e",
+        "outputId": "e4096d0c-156e-4247-94af-783550af7319"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/html": [
+              "<div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>rating_int</th>\n",
+              "      <th>confidence_int</th>\n",
+              "      <th>conf_year</th>\n",
+              "      <th>review_num_tokens</th>\n",
+              "      <th>tcdate</th>\n",
+              "      <th>tmdate</th>\n",
+              "      <th>number</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>rating_int</th>\n",
+              "      <td>1.000000</td>\n",
+              "      <td>-0.592927</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>-0.392889</td>\n",
+              "      <td>0.375000</td>\n",
+              "      <td>-0.375000</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>confidence_int</th>\n",
+              "      <td>-0.592927</td>\n",
+              "      <td>1.000000</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0.651335</td>\n",
+              "      <td>-0.395285</td>\n",
+              "      <td>0.395285</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>conf_year</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>review_num_tokens</th>\n",
+              "      <td>-0.392889</td>\n",
+              "      <td>0.651335</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>1.000000</td>\n",
+              "      <td>0.245726</td>\n",
+              "      <td>-0.245726</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>tcdate</th>\n",
+              "      <td>0.375000</td>\n",
+              "      <td>-0.395285</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>0.245726</td>\n",
+              "      <td>1.000000</td>\n",
+              "      <td>-1.000000</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>tmdate</th>\n",
+              "      <td>-0.375000</td>\n",
+              "      <td>0.395285</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>-0.245726</td>\n",
+              "      <td>-1.000000</td>\n",
+              "      <td>1.000000</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>number</th>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "      <td>NaN</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "                   rating_int  confidence_int  conf_year  review_num_tokens  \\\n",
+              "rating_int           1.000000       -0.592927        NaN          -0.392889   \n",
+              "confidence_int      -0.592927        1.000000        NaN           0.651335   \n",
+              "conf_year                 NaN             NaN        NaN                NaN   \n",
+              "review_num_tokens   -0.392889        0.651335        NaN           1.000000   \n",
+              "tcdate               0.375000       -0.395285        NaN           0.245726   \n",
+              "tmdate              -0.375000        0.395285        NaN          -0.245726   \n",
+              "number                    NaN             NaN        NaN                NaN   \n",
+              "\n",
+              "                     tcdate    tmdate  number  \n",
+              "rating_int         0.375000 -0.375000     NaN  \n",
+              "confidence_int    -0.395285  0.395285     NaN  \n",
+              "conf_year               NaN       NaN     NaN  \n",
+              "review_num_tokens  0.245726 -0.245726     NaN  \n",
+              "tcdate             1.000000 -1.000000     NaN  \n",
+              "tmdate            -1.000000  1.000000     NaN  \n",
+              "number                  NaN       NaN     NaN  "
+            ]
+          },
+          "execution_count": 34,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "df_combined_model.corr(numeric_only=True)"
+      ]
+    }
+  ],
+  "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": "3.10.4"
+    },
+    "colab": {
+      "provenance": []
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file