{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "3a8a2e23",
   "metadata": {},
   "source": [
    "# Activity: Improving sentiment analysis with convolutional layers\n",
    "\n",
    "**Note**: this notebook is part of the complete lesson 34 repository [`gperdrizet/RNNs`](https://github.com/gperdrizet/RNNs) and is intended to be run in the environment set-up by that repository.\n",
    "\n",
    "## Objective\n",
    "\n",
    "In this activity, you will extend the baseline RNN sentiment classifier by adding **convolutional layers** to create a hybrid CNN-RNN architecture. Convolutional layers can capture local n-gram patterns (like \"not good\" or \"very happy\") before the recurrent layers process the sequence.\n",
    "\n",
    "**Your tasks:**\n",
    "1. Run the baseline GRU model and note its performance\n",
    "2. Modify the model architecture to include convolutional layers\n",
    "3. Train your CNN-RNN hybrid model\n",
    "4. Compare the results to the baseline\n",
    "\n",
    "---\n",
    "\n",
    "- **Tokenization**: Splitting text into individual units (tokens), typically words. For example, \"I love this!\" becomes `[\"i\", \"love\", \"this\"]`. This is the first step in converting text to a format neural networks can process.\n",
    "\n",
    "- **Embedding**: A dense vector representation of a token. Instead of one-hot encoding (sparse, high-dimensional), embeddings map each word to a fixed-size vector (e.g., 100 dimensions) where similar words have similar vectors. We use pretrained GloVe embeddings trained on Twitter data.\n",
    "\n",
    "- **LSTM/GRU**: Variants of RNNs designed to handle long sequences better than SimpleRNN. They use \"gates\" to control information flow, solving the vanishing gradient problem. **GRU** (Gated Recurrent Unit) has 2 gates and is simpler; **LSTM** (Long Short-Term Memory) has 3 gates and more parameters. Both work well in practice — we use GRU here for efficiency.\n",
    "\n",
    "## How the GRU processes a sequence\n",
    "\n",
    "Given input sequence `[\"i\", \"love\", \"this]`, the GRU predicts sentiment:\n",
    "\n",
    "```text\n",
    "\n",
    "                   ┌────────────◀───────────┐ 'h₁', then 'h₂'\n",
    "                   ▼                        │\n",
    "                ╔══════════════════════════════╗\n",
    "                ║  │           GRU          ▲  ║\n",
    "                ║  │                        │  ║\n",
    "  'I' then,     ║  ├──▶Reset───▶candidate──▶│  ║         ╔═══════╗ \n",
    "'love', then ══▶║  │   gate      hidden     │  ╠══'h₃'══▶║ Dense ╠══▶ Sentiment\n",
    "   'this'       ║  │              state     │  ║         ╚═══════╝\n",
    "                ║  │                        │  ║\n",
    "                ║  └─────▶Update gate───────┘  ║\n",
    "                ╚══════════════════════════════╝\n",
    "\n",
    "```\n",
    "## Key terms\n",
    "\n",
    "- **Reset gate**: Controls how much the prior hidden state influences the new candidate hidden state. Gates are **dynamic weights** (0-1) — one per hidden unit — computed fresh for each input. Depend on **both** the previous hidden state AND the current input.\n",
    "- **Update gate**: Controls how much prior hidden state vs new candidate hidden state goes into the new hidden state. Also computed from previous hidden state + current input, just with different learned weights.\n",
    "- **Bidirectional recurrent layers**: Processes a sequence in both directions (forward and backward) and combines the results. This allows the model to use context from both before AND after each word, improving understanding.\n",
    "\n",
    "## External tools & resources\n",
    "\n",
    "- **Stopwords**: Common words (e.g., \"the\", \"is\", \"at\") filtered out during preprocessing to reduce noise and focus on meaningful content.\n",
    "  - *This project*: [NLTK Stopwords](https://www.nltk.org/nltk_data/) — curated lists for 20+ languages\n",
    "  - *Alternatives*: [spaCy stopwords](https://spacy.io/usage/rule-based-matching#vocab-stopwords), [scikit-learn ENGLISH_STOP_WORDS](https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.ENGLISH_STOP_WORDS.html)\n",
    "\n",
    "- **Tokenizers**: Tools that split text into tokens. Different tokenizers handle edge cases differently — social media text requires special handling for emoticons, hashtags, and informal spelling.\n",
    "  - *This project*: [NLTK TweetTokenizer](https://www.nltk.org/api/nltk.tokenize.casual.html#nltk.tokenize.casual.TweetTokenizer) — handles emoticons, hashtags, mentions, and normalizes repeated characters (e.g., \"sooooo\" → \"sooo\")\n",
    "  - *Alternatives*: [spaCy Tokenizer](https://spacy.io/usage/linguistic-features#tokenization), [Hugging Face Tokenizers](https://huggingface.co/docs/tokenizers/), [NLTK word_tokenize](https://www.nltk.org/api/nltk.tokenize.word_tokenize.html)\n",
    "\n",
    "- **Word Embeddings**: Pretrained vector representations that capture semantic relationships between words. Using pretrained embeddings transfers knowledge from large corpora to your model.\n",
    "  - *This project*: [GloVe Twitter embeddings](https://nlp.stanford.edu/projects/glove/) — trained on 27B Twitter tokens, 100 dimensions\n",
    "  - *Alternatives*: [Word2Vec](https://radimrehurek.com/gensim/models/word2vec.html), [FastText](https://fasttext.cc/docs/en/english-vectors.html), [Hugging Face sentence-transformers](https://huggingface.co/sentence-transformers)\n",
    "\n",
    "\n",
    "## Notebook setup\n",
    "\n",
    "### Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2c49205e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import re\n",
    "import zipfile\n",
    "import urllib.request\n",
    "from collections import Counter\n",
    "\n",
    "import nltk\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import tensorflow as tf\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import (\n",
    "    Embedding, Dense, GRU, Dropout, Bidirectional, SpatialDropout1D\n",
    ")\n",
    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, TensorBoard\n",
    "from tensorflow.keras.regularizers import l2\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.utils.class_weight import compute_class_weight\n",
    "from sklearn.metrics import confusion_matrix, roc_curve, auc, precision_recall_curve\n",
    "from sklearn.preprocessing import label_binarize\n",
    "\n",
    "# Download NLTK resources\n",
    "nltk.download('stopwords', quiet=True)\n",
    "from nltk.corpus import stopwords\n",
    "from nltk.tokenize import TweetTokenizer"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "664d2ca9",
   "metadata": {},
   "source": [
    "### Configuration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b8d56b31",
   "metadata": {},
   "outputs": [],
   "source": [
    "stop_words = set(stopwords.words('english'))\n",
    "tweet_tokenizer = TweetTokenizer(preserve_case=False, reduce_len=True, strip_handles=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dc9b3cef",
   "metadata": {},
   "source": [
    "## 1. Data preparation\n",
    "\n",
    "### 1.1. Load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "08292db5",
   "metadata": {},
   "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>name</th>\n",
       "      <th>score</th>\n",
       "      <th>text</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>638060586258038784</td>\n",
       "      <td>michael jackson</td>\n",
       "      <td>0</td>\n",
       "      <td>05 Beat it - Michael Jackson - Thriller (25th ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>638061181823922176</td>\n",
       "      <td>michael jackson</td>\n",
       "      <td>1</td>\n",
       "      <td>Jay Z joins Instagram with nostalgic tribute t...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>638083821364244480</td>\n",
       "      <td>michael jackson</td>\n",
       "      <td>0</td>\n",
       "      <td>Michael Jackson: Bad 25th Anniversary Edition ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>638091450132078593</td>\n",
       "      <td>michael jackson</td>\n",
       "      <td>1</td>\n",
       "      <td>I liked a @YouTube video http://t.co/AaR3pjp2P...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>638125563790557184</td>\n",
       "      <td>michael jackson</td>\n",
       "      <td>1</td>\n",
       "      <td>18th anniv of Princess Diana's death. I still ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   id             name  score  \\\n",
       "0  638060586258038784  michael jackson      0   \n",
       "1  638061181823922176  michael jackson      1   \n",
       "2  638083821364244480  michael jackson      0   \n",
       "3  638091450132078593  michael jackson      1   \n",
       "4  638125563790557184  michael jackson      1   \n",
       "\n",
       "                                                text  \n",
       "0  05 Beat it - Michael Jackson - Thriller (25th ...  \n",
       "1  Jay Z joins Instagram with nostalgic tribute t...  \n",
       "2  Michael Jackson: Bad 25th Anniversary Edition ...  \n",
       "3  I liked a @YouTube video http://t.co/AaR3pjp2P...  \n",
       "4  18th anniv of Princess Diana's death. I still ...  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_parquet('../data/twitter-2016.parquet')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "52be2521",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 30467 entries, 0 to 30466\n",
      "Data columns (total 4 columns):\n",
      " #   Column  Non-Null Count  Dtype \n",
      "---  ------  --------------  ----- \n",
      " 0   id      30467 non-null  int64 \n",
      " 1   name    30467 non-null  object\n",
      " 2   score   30467 non-null  int64 \n",
      " 3   text    30467 non-null  object\n",
      "dtypes: int64(2), object(2)\n",
      "memory usage: 952.2+ KB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4b4c04aa",
   "metadata": {},
   "source": [
    "### 1.2. Clean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf67ece0",
   "metadata": {},
   "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>text</th>\n",
       "      <th>tokens</th>\n",
       "      <th>score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>05 Beat it - Michael Jackson - Thriller (25th ...</td>\n",
       "      <td>[05, beat, michael, jackson, thriller, 25th, a...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Jay Z joins Instagram with nostalgic tribute t...</td>\n",
       "      <td>[jay, joins, instagram, nostalgic, tribute, mi...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Michael Jackson: Bad 25th Anniversary Edition ...</td>\n",
       "      <td>[michael, jackson, bad, 25th, anniversary, edi...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>I liked a @YouTube video http://t.co/AaR3pjp2P...</td>\n",
       "      <td>[liked, video, one, direction, singing, man, m...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>18th anniv of Princess Diana's death. I still ...</td>\n",
       "      <td>[18th, anniv, princess, diana's, death, still,...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text  \\\n",
       "0  05 Beat it - Michael Jackson - Thriller (25th ...   \n",
       "1  Jay Z joins Instagram with nostalgic tribute t...   \n",
       "2  Michael Jackson: Bad 25th Anniversary Edition ...   \n",
       "3  I liked a @YouTube video http://t.co/AaR3pjp2P...   \n",
       "4  18th anniv of Princess Diana's death. I still ...   \n",
       "\n",
       "                                              tokens  score  \n",
       "0  [05, beat, michael, jackson, thriller, 25th, a...      0  \n",
       "1  [jay, joins, instagram, nostalgic, tribute, mi...      1  \n",
       "2  [michael, jackson, bad, 25th, anniversary, edi...      0  \n",
       "3  [liked, video, one, direction, singing, man, m...      1  \n",
       "4  [18th, anniv, princess, diana's, death, still,...      1  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Clean data - drop rows with missing scores\n",
    "df_clean = df.dropna(subset=['score']).copy()\n",
    "df_clean['score'] = df_clean['score'].astype(int)\n",
    "\n",
    "# Shift scores to 0-based index: [-2,-1,0,1,2] -> [0,1,2,3,4]\n",
    "score_min = df_clean['score'].min()\n",
    "df_clean['score_shifted'] = df_clean['score'] - score_min\n",
    "\n",
    "print(f'Cleaned dataset: {len(df_clean):,} rows ({len(df) - len(df_clean):,} dropped)')\n",
    "print(f'Score distribution: {df_clean[\"score_shifted\"].value_counts().sort_index().to_dict()}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b45c1eb",
   "metadata": {},
   "source": [
    "### 1.3. Tokenize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2b7efdeb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Clean and tokenize text using NLTK's TweetTokenizer\n",
    "def clean_text(text):\n",
    "    '''Clean and tokenize tweet text using TweetTokenizer.'''\n",
    "\n",
    "    if not isinstance(text, str):\n",
    "        return []\n",
    "\n",
    "    # Remove URLs before tokenizing\n",
    "    text = re.sub(r'http\\S+|www\\S+|https\\S+', '', text)\n",
    "\n",
    "    # TweetTokenizer handles: lowercase, @mentions, repeated chars (e.g., sooooo -> sooo)\n",
    "    tokens = tweet_tokenizer.tokenize(text)\n",
    "\n",
    "    # Remove stopwords and single characters\n",
    "    tokens = [t for t in tokens if t not in stop_words and len(t) > 1]\n",
    "\n",
    "    return tokens\n",
    "\n",
    "# Apply tokenization\n",
    "df_clean['tokens'] = df_clean['text'].apply(clean_text)\n",
    "df_clean[['text', 'tokens', 'score']].head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9a70b43c",
   "metadata": {},
   "source": [
    "### 1.4. Build vocabulary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0d8efd85",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Vocabulary size: 14965\n"
     ]
    }
   ],
   "source": [
    "# Build vocabulary\n",
    "def build_vocab(token_lists, min_freq=2):\n",
    "    '''Build vocabulary from token lists.'''\n",
    "\n",
    "    counter = Counter()\n",
    "\n",
    "    for tokens in token_lists:\n",
    "        counter.update(tokens)\n",
    "    \n",
    "    # Filter by minimum frequency and create vocab\n",
    "    vocab = {'<PAD>': 0, '<UNK>': 1}\n",
    "\n",
    "    for word, freq in counter.items():\n",
    "        if freq >= min_freq:\n",
    "            vocab[word] = len(vocab)\n",
    "\n",
    "    return vocab\n",
    "\n",
    "vocab = build_vocab(df_clean['tokens'])\n",
    "print(f'Vocabulary size: {len(vocab)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cc6059bd",
   "metadata": {},
   "source": [
    "### 1.5. Convert to indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "951ab5c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "def tokens_to_indices(tokens_list, vocab, max_len=50):\n",
    "    '''Convert token lists to padded index sequences.'''\n",
    "\n",
    "    sequences = []\n",
    "\n",
    "    for tokens in tokens_list:\n",
    "        indices = [vocab.get(token, vocab['<UNK>']) for token in tokens]\n",
    "        sequences.append(indices)\n",
    "\n",
    "    # Pad sequences to max_len\n",
    "    return pad_sequences(sequences, maxlen=max_len, padding='post', value=vocab['<PAD>'])\n",
    "\n",
    "# Convert all data to indices\n",
    "max_len = 50\n",
    "X = tokens_to_indices(df_clean['tokens'].tolist(), vocab, max_len)\n",
    "y = df_clean['score_shifted'].values\n",
    "\n",
    "print(f'X shape: {X.shape}')\n",
    "print(f'y shape: {y.shape}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5118247a",
   "metadata": {},
   "source": [
    "### 1.6. Train/test split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c941eef5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train shape: (24373, 50)\n",
      "y_train shape: (24373,)\n",
      "Score distribution (train): Counter({2: 10362, 3: 10249, 1: 2714, 4: 809, 0: 239})\n"
     ]
    }
   ],
   "source": [
    "# Train/test split\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y,\n",
    "    test_size=0.2,\n",
    "    random_state=42,\n",
    "    stratify=y\n",
    ")\n",
    "\n",
    "print(f'X_train shape: {X_train.shape}')\n",
    "print(f'X_test shape: {X_test.shape}')\n",
    "print(f'Score distribution (train): {Counter(y_train)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45f38bea",
   "metadata": {},
   "source": [
    "## 2. Prepare GloVe embeddings\n",
    "\n",
    "GloVe (Global Vectors) provides pretrained word embeddings trained on large text corpora. Using these gives our model a head start - words already have meaningful representations instead of random vectors.\n",
    "\n",
    "### 2.1. Download embeddings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "74bb2bfa",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "GloVe file already exists: ../data/glove.twitter.27B.100d.txt\n"
     ]
    }
   ],
   "source": [
    "# Download GloVe embeddings (Twitter-specific, 100d)\n",
    "glove_dir = '../data'\n",
    "glove_file = os.path.join(glove_dir, 'glove.twitter.27B.100d.txt')\n",
    "glove_zip = os.path.join(glove_dir, 'glove.twitter.27B.zip')\n",
    "glove_url = 'https://nlp.stanford.edu/data/glove.twitter.27B.zip'\n",
    "\n",
    "if not os.path.exists(glove_file):\n",
    "\n",
    "    print('Downloading GloVe embeddings...')\n",
    "    urllib.request.urlretrieve(glove_url, glove_zip)\n",
    "\n",
    "    print('Extracting...')\n",
    "    with zipfile.ZipFile(glove_zip, 'r') as zip_ref:\n",
    "        zip_ref.extract('glove.twitter.27B.100d.txt', glove_dir)\n",
    "\n",
    "    os.remove(glove_zip)\n",
    "    print('Done!')\n",
    "\n",
    "else:\n",
    "    print(f'GloVe file already exists: {glove_file}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "61a52fea",
   "metadata": {},
   "source": [
    "### 2.2. Load embeddings into dictionary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5cf57e38",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading GloVe vectors...\n",
      "Loaded 1,193,514 word vectors\n",
      "Embedding dimension: 100\n"
     ]
    }
   ],
   "source": [
    "# Load GloVe vectors into dictionary\n",
    "print('Loading GloVe vectors...')\n",
    "\n",
    "glove_vectors = {}\n",
    "\n",
    "with open(glove_file, 'r', encoding='utf-8') as f:\n",
    "    for line in f:\n",
    "\n",
    "        values = line.split()\n",
    "        word = values[0]\n",
    "        vector = np.array(values[1:], dtype='float32')\n",
    "        glove_vectors[word] = vector\n",
    "\n",
    "print(f'Loaded {len(glove_vectors):,} word vectors')\n",
    "print(f'Embedding dimension: {len(next(iter(glove_vectors.values())))}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "229ff779",
   "metadata": {},
   "source": [
    "### 2.3. Create embedding look-up table for our vocabulary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d1cc20ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Vocabulary coverage: 12,976 / 14,965 (86.7%)\n",
      "Embedding matrix shape: (14965, 100)\n"
     ]
    }
   ],
   "source": [
    "# Create embedding matrix for our vocabulary\n",
    "embedding_dim = 100  # GloVe Twitter uses 100d\n",
    "vocab_size = len(vocab)\n",
    "\n",
    "embedding_matrix = np.zeros((vocab_size, embedding_dim))\n",
    "words_found = 0\n",
    "\n",
    "for word, idx in vocab.items():\n",
    "    if word in glove_vectors:\n",
    "        embedding_matrix[idx] = glove_vectors[word]\n",
    "        words_found += 1\n",
    "\n",
    "    else:\n",
    "        # Random initialization for words not in GloVe\n",
    "        embedding_matrix[idx] = np.random.normal(scale=0.6, size=(embedding_dim,))\n",
    "\n",
    "coverage = words_found / vocab_size\n",
    "print(f'Vocabulary coverage: {words_found:,} / {vocab_size:,} ({coverage:.1%})')\n",
    "print(f'Embedding matrix shape: {embedding_matrix.shape}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e889cccf",
   "metadata": {},
   "source": [
    "## 3. Baseline: Bidirectional GRU model\n",
    "\n",
    "First, let's establish our baseline performance with a pure recurrent architecture.\n",
    "\n",
    "### 3.1. Build model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d90c1cf5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " embedding (Embedding)       (None, None, 100)         1496500   \n",
      "                                                                 \n",
      " spatial_dropout1d (Spatial  (None, None, 100)         0         \n",
      " Dropout1D)                                                      \n",
      "                                                                 \n",
      " bidirectional (Bidirection  (None, None, 128)         63744     \n",
      " al)                                                             \n",
      "                                                                 \n",
      " bidirectional_1 (Bidirecti  (None, 64)                31104     \n",
      " onal)                                                           \n",
      "                                                                 \n",
      " dropout (Dropout)           (None, 64)                0         \n",
      "                                                                 \n",
      " dense (Dense)               (None, 5)                 325       \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 1591673 (6.07 MB)\n",
      "Trainable params: 1591673 (6.07 MB)\n",
      "Non-trainable params: 0 (0.00 Byte)\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "# Model hyperparameters\n",
    "hidden_dim = 64\n",
    "output_dim = len(set(y_train))\n",
    "dropout = 0.3            # Spatial dropout rate\n",
    "recurrent_dropout = 0.3  # Dropout on recurrent connections\n",
    "l2_reg = 0.01            # L2 regularization strength\n",
    "learning_rate = 0.0001   # Lower LR for fine-tuning embeddings\n",
    "\n",
    "# Build Bidirectional GRU model with pretrained GloVe embeddings\n",
    "model = Sequential([\n",
    "    Embedding(\n",
    "        vocab_size, \n",
    "        embedding_dim,\n",
    "        weights=[embedding_matrix],\n",
    "        trainable=True  # Fine-tune embeddings with lower learning rate\n",
    "    ),\n",
    "    SpatialDropout1D(dropout),\n",
    "    Bidirectional(GRU(hidden_dim, recurrent_dropout=recurrent_dropout, return_sequences=True)),\n",
    "    Bidirectional(GRU(hidden_dim // 2, recurrent_dropout=recurrent_dropout)),  # Second layer, smaller\n",
    "    Dropout(dropout),\n",
    "    Dense(output_dim, activation='softmax', kernel_regularizer=l2(l2_reg))\n",
    "])\n",
    "\n",
    "model.compile(\n",
    "    optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),\n",
    "    loss='sparse_categorical_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1f4d6bcf",
   "metadata": {},
   "source": [
    "### 3.2. Define training callbacks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "9e1fb763",
   "metadata": {},
   "outputs": [],
   "source": [
    "callbacks = [\n",
    "    ModelCheckpoint(\n",
    "        '../models/rnn_classifier.keras',\n",
    "        save_best_only=True,\n",
    "        monitor='val_accuracy',\n",
    "        verbose=1\n",
    "    ),\n",
    "    EarlyStopping(\n",
    "        monitor='val_loss',\n",
    "        patience=5,\n",
    "        restore_best_weights=True,\n",
    "        verbose=1\n",
    "    ),\n",
    "    TensorBoard(\n",
    "        log_dir='../logs/rnn_classifier',\n",
    "        histogram_freq=1,\n",
    "        write_graph=True\n",
    "    )\n",
    "]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9cae247",
   "metadata": {},
   "source": [
    "### 3.3. Calculate class weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f10adb3a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Class weights: {0: 20.39581589958159, 1: 1.7960943257184967, 2: 0.47043041883806214, 3: 0.47561713337886624, 4: 6.025463535228678}\n"
     ]
    }
   ],
   "source": [
    "class_weights = compute_class_weight('balanced', classes=np.unique(y_train), y=y_train)\n",
    "class_weight_dict = dict(enumerate(class_weights))\n",
    "print(f'Class weights: {class_weight_dict}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0791aaeb",
   "metadata": {},
   "source": [
    "### 3.4. Train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9fb97944",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "I0000 00:00:1770934211.831974 1510527 service.cc:145] XLA service 0x7cc584144290 initialized for platform Host (this does not guarantee that XLA will be used). Devices:\n",
      "I0000 00:00:1770934211.832054 1510527 service.cc:153]   StreamExecutor device (0): Host, Default Version\n",
      "I0000 00:00:1770934211.924345 1510527 device_compiler.h:188] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "381/381 [==============================] - ETA: 0s - loss: 1.7151 - accuracy: 0.1988\n",
      "Epoch 1: val_accuracy improved from -inf to 0.28356, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 88s 117ms/step - loss: 1.7151 - accuracy: 0.1988 - val_loss: 1.6417 - val_accuracy: 0.2836\n",
      "Epoch 2/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.6190 - accuracy: 0.2350\n",
      "Epoch 2: val_accuracy improved from 0.28356 to 0.29833, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 31s 82ms/step - loss: 1.6190 - accuracy: 0.2350 - val_loss: 1.5609 - val_accuracy: 0.2983\n",
      "Epoch 3/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.5272 - accuracy: 0.2526\n",
      "Epoch 3: val_accuracy did not improve from 0.29833\n",
      "381/381 [==============================] - 30s 79ms/step - loss: 1.5272 - accuracy: 0.2526 - val_loss: 1.5832 - val_accuracy: 0.1666\n",
      "Epoch 4/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.4679 - accuracy: 0.2619\n",
      "Epoch 4: val_accuracy did not improve from 0.29833\n",
      "381/381 [==============================] - 30s 79ms/step - loss: 1.4679 - accuracy: 0.2619 - val_loss: 1.5399 - val_accuracy: 0.2094\n",
      "Epoch 5/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.4279 - accuracy: 0.2729\n",
      "Epoch 5: val_accuracy did not improve from 0.29833\n",
      "381/381 [==============================] - 29s 77ms/step - loss: 1.4279 - accuracy: 0.2729 - val_loss: 1.4849 - val_accuracy: 0.2778\n",
      "Epoch 6/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.3805 - accuracy: 0.3021\n",
      "Epoch 6: val_accuracy improved from 0.29833 to 0.30341, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 30s 78ms/step - loss: 1.3805 - accuracy: 0.3021 - val_loss: 1.4422 - val_accuracy: 0.3034\n",
      "Epoch 7/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.3434 - accuracy: 0.3058\n",
      "Epoch 7: val_accuracy improved from 0.30341 to 0.30604, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 30s 80ms/step - loss: 1.3434 - accuracy: 0.3058 - val_loss: 1.4294 - val_accuracy: 0.3060\n",
      "Epoch 8/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.3179 - accuracy: 0.3251\n",
      "Epoch 8: val_accuracy did not improve from 0.30604\n",
      "381/381 [==============================] - 30s 80ms/step - loss: 1.3179 - accuracy: 0.3251 - val_loss: 1.5057 - val_accuracy: 0.3003\n",
      "Epoch 9/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.2875 - accuracy: 0.3445\n",
      "Epoch 9: val_accuracy improved from 0.30604 to 0.36183, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 32s 83ms/step - loss: 1.2875 - accuracy: 0.3445 - val_loss: 1.3831 - val_accuracy: 0.3618\n",
      "Epoch 10/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.2531 - accuracy: 0.3544\n",
      "Epoch 10: val_accuracy improved from 0.36183 to 0.38694, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 30s 78ms/step - loss: 1.2531 - accuracy: 0.3544 - val_loss: 1.3730 - val_accuracy: 0.3869\n",
      "Epoch 11/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.2185 - accuracy: 0.3665\n",
      "Epoch 11: val_accuracy improved from 0.38694 to 0.42238, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 30s 80ms/step - loss: 1.2185 - accuracy: 0.3665 - val_loss: 1.2793 - val_accuracy: 0.4224\n",
      "Epoch 12/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.2001 - accuracy: 0.3814\n",
      "Epoch 12: val_accuracy did not improve from 0.42238\n",
      "381/381 [==============================] - 30s 78ms/step - loss: 1.2001 - accuracy: 0.3814 - val_loss: 1.2758 - val_accuracy: 0.4202\n",
      "Epoch 13/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.1732 - accuracy: 0.3832\n",
      "Epoch 13: val_accuracy did not improve from 0.42238\n",
      "381/381 [==============================] - 29s 77ms/step - loss: 1.1732 - accuracy: 0.3832 - val_loss: 1.3741 - val_accuracy: 0.3723\n",
      "Epoch 14/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.1533 - accuracy: 0.4018\n",
      "Epoch 14: val_accuracy did not improve from 0.42238\n",
      "381/381 [==============================] - 31s 81ms/step - loss: 1.1533 - accuracy: 0.4018 - val_loss: 1.2930 - val_accuracy: 0.4058\n",
      "Epoch 15/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.1253 - accuracy: 0.4067\n",
      "Epoch 15: val_accuracy did not improve from 0.42238\n",
      "381/381 [==============================] - 30s 79ms/step - loss: 1.1253 - accuracy: 0.4067 - val_loss: 1.3519 - val_accuracy: 0.3695\n",
      "Epoch 16/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0960 - accuracy: 0.4192\n",
      "Epoch 16: val_accuracy improved from 0.42238 to 0.44946, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 30s 78ms/step - loss: 1.0960 - accuracy: 0.4192 - val_loss: 1.2161 - val_accuracy: 0.4495\n",
      "Epoch 17/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0880 - accuracy: 0.4238\n",
      "Epoch 17: val_accuracy did not improve from 0.44946\n",
      "381/381 [==============================] - 30s 78ms/step - loss: 1.0880 - accuracy: 0.4238 - val_loss: 1.2489 - val_accuracy: 0.4306\n",
      "Epoch 18/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0560 - accuracy: 0.4315\n",
      "Epoch 18: val_accuracy did not improve from 0.44946\n",
      "381/381 [==============================] - 29s 76ms/step - loss: 1.0560 - accuracy: 0.4315 - val_loss: 1.2604 - val_accuracy: 0.4406\n",
      "Epoch 19/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0475 - accuracy: 0.4404\n",
      "Epoch 19: val_accuracy did not improve from 0.44946\n",
      "381/381 [==============================] - 31s 80ms/step - loss: 1.0475 - accuracy: 0.4404 - val_loss: 1.2675 - val_accuracy: 0.4222\n",
      "Epoch 20/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0282 - accuracy: 0.4468\n",
      "Epoch 20: val_accuracy did not improve from 0.44946\n",
      "381/381 [==============================] - 29s 76ms/step - loss: 1.0282 - accuracy: 0.4468 - val_loss: 1.2536 - val_accuracy: 0.4319\n",
      "Epoch 21/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 1.0081 - accuracy: 0.4439\n",
      "Epoch 21: val_accuracy improved from 0.44946 to 0.48179, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 28s 75ms/step - loss: 1.0081 - accuracy: 0.4439 - val_loss: 1.1679 - val_accuracy: 0.4818\n",
      "Epoch 22/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9995 - accuracy: 0.4491\n",
      "Epoch 22: val_accuracy did not improve from 0.48179\n",
      "381/381 [==============================] - 29s 76ms/step - loss: 0.9995 - accuracy: 0.4491 - val_loss: 1.1914 - val_accuracy: 0.4637\n",
      "Epoch 23/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9886 - accuracy: 0.4558\n",
      "Epoch 23: val_accuracy improved from 0.48179 to 0.48835, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 29s 75ms/step - loss: 0.9886 - accuracy: 0.4558 - val_loss: 1.1515 - val_accuracy: 0.4883\n",
      "Epoch 24/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9780 - accuracy: 0.4651\n",
      "Epoch 24: val_accuracy did not improve from 0.48835\n",
      "381/381 [==============================] - 28s 74ms/step - loss: 0.9780 - accuracy: 0.4651 - val_loss: 1.1548 - val_accuracy: 0.4862\n",
      "Epoch 25/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9532 - accuracy: 0.4706\n",
      "Epoch 25: val_accuracy did not improve from 0.48835\n",
      "381/381 [==============================] - 28s 75ms/step - loss: 0.9532 - accuracy: 0.4706 - val_loss: 1.1777 - val_accuracy: 0.4716\n",
      "Epoch 26/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9407 - accuracy: 0.4727\n",
      "Epoch 26: val_accuracy did not improve from 0.48835\n",
      "381/381 [==============================] - 29s 75ms/step - loss: 0.9407 - accuracy: 0.4727 - val_loss: 1.1545 - val_accuracy: 0.4844\n",
      "Epoch 27/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9358 - accuracy: 0.4786\n",
      "Epoch 27: val_accuracy did not improve from 0.48835\n",
      "381/381 [==============================] - 28s 74ms/step - loss: 0.9358 - accuracy: 0.4786 - val_loss: 1.1462 - val_accuracy: 0.4875\n",
      "Epoch 28/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9218 - accuracy: 0.4830\n",
      "Epoch 28: val_accuracy improved from 0.48835 to 0.49409, saving model to ../models/rnn_classifier.keras\n",
      "381/381 [==============================] - 29s 75ms/step - loss: 0.9218 - accuracy: 0.4830 - val_loss: 1.1333 - val_accuracy: 0.4941\n",
      "Epoch 29/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9172 - accuracy: 0.4876\n",
      "Epoch 29: val_accuracy did not improve from 0.49409\n",
      "381/381 [==============================] - 29s 75ms/step - loss: 0.9172 - accuracy: 0.4876 - val_loss: 1.1498 - val_accuracy: 0.4887\n",
      "Epoch 30/30\n",
      "381/381 [==============================] - ETA: 0s - loss: 0.9071 - accuracy: 0.4901\n",
      "Epoch 30: val_accuracy did not improve from 0.49409\n",
      "381/381 [==============================] - 29s 75ms/step - loss: 0.9071 - accuracy: 0.4901 - val_loss: 1.1522 - val_accuracy: 0.4861\n",
      "Restoring model weights from the end of the best epoch: 28.\n"
     ]
    }
   ],
   "source": [
    "# Training with class weighting and early stopping\n",
    "history = model.fit(\n",
    "    X_train, y_train,\n",
    "    validation_data=(X_test, y_test),\n",
    "    epochs=30,\n",
    "    batch_size=64,\n",
    "    class_weight=class_weight_dict,\n",
    "    callbacks=callbacks\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "72de8d3b",
   "metadata": {},
   "source": [
    "## 4. Baseline evaluation\n",
    "\n",
    "Record the baseline metrics below so you can compare them to your CNN-RNN model later.\n",
    "\n",
    "### 4.1. Make test set predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "7342f545",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "191/191 [==============================] - 6s 16ms/step\n",
      "Test samples: 6094\n",
      "Prediction distribution:\n",
      "  Actual:    Counter({2: 2591, 3: 2563, 1: 678, 4: 202, 0: 60})\n",
      "  Predicted: Counter({2: 2083, 3: 1856, 1: 1150, 4: 856, 0: 149})\n"
     ]
    }
   ],
   "source": [
    "# Load best model and get predictions\n",
    "model = tf.keras.models.load_model('../models/rnn_classifier.keras')\n",
    "\n",
    "# Get predicted probabilities and classes\n",
    "y_prob = model.predict(X_test)\n",
    "y_pred = y_prob.argmax(axis=1)\n",
    "\n",
    "# Class labels\n",
    "class_names = ['-2', '-1', '0', '1', '2']\n",
    "n_classes = len(class_names)\n",
    "\n",
    "print(f'Test samples: {len(y_test)}')\n",
    "print(f'Prediction distribution:')\n",
    "print(f'  Actual:    {Counter(y_test)}')\n",
    "print(f'  Predicted: {Counter(y_pred)}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "408d5b20",
   "metadata": {},
   "source": [
    "### 4.2. Per-class accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "89df382c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Per-class accuracy table\n",
    "per_class_stats = []\n",
    "\n",
    "for i, class_name in enumerate(class_names):\n",
    "    mask = y_test == i\n",
    "    n_samples = mask.sum()\n",
    "    n_correct = (y_pred[mask] == i).sum()\n",
    "    accuracy = n_correct / n_samples if n_samples > 0 else 0\n",
    "    \n",
    "    per_class_stats.append({\n",
    "        'Class': class_name,\n",
    "        'Samples': n_samples,\n",
    "        'Correct': n_correct,\n",
    "        'Accuracy': f'{accuracy:.1%}'\n",
    "    })\n",
    "\n",
    "# Add overall accuracy\n",
    "overall_acc = (y_pred == y_test).mean()\n",
    "per_class_stats.append({\n",
    "    'Class': 'Overall',\n",
    "    'Samples': len(y_test),\n",
    "    'Correct': (y_pred == y_test).sum(),\n",
    "    'Accuracy': f'{overall_acc:.1%}'\n",
    "})\n",
    "\n",
    "accuracy_df = pd.DataFrame(per_class_stats)\n",
    "accuracy_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "296a3976",
   "metadata": {},
   "source": [
    "### 4.3. Confusion matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "02d44a72",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1500x300 with 5 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot confusion matrix\n",
    "fig, ax = plt.subplots(figsize=(8, 6))\n",
    "\n",
    "ax.set_title('Confusion matrix')\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "sns.heatmap(\n",
    "    cm, \n",
    "    annot=True, fmt='d', cmap='Blues', \n",
    "    xticklabels=class_names, yticklabels=class_names, ax=ax\n",
    ")\n",
    "\n",
    "ax.set_xlabel('Predicted')\n",
    "ax.set_ylabel('Actual')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7895bdbc",
   "metadata": {},
   "source": [
    "### 4.4. Predicted probability distributions by class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91f28172",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Predicted probability distributions for each true class\n",
    "fig, axes = plt.subplots(1, n_classes, figsize=(10, 2.5))\n",
    "\n",
    "plt.suptitle('Predicted probability distributions by true class', y=1.02)\n",
    "\n",
    "for i, class_name in enumerate(class_names):\n",
    "\n",
    "    # Get predictions for samples of this true class\n",
    "    mask = y_test == i\n",
    "    probs_for_class = y_prob[mask]\n",
    "    \n",
    "    # Plot distribution of predicted probabilities for each predicted class\n",
    "    ax = axes[i]\n",
    "    ax.boxplot([probs_for_class[:, j] for j in range(n_classes)], tick_labels=class_names)\n",
    "    ax.set_title(f'True class: {class_name}')\n",
    "    ax.set_xlabel('Predicted class')\n",
    "    ax.set_ylabel('Probability')\n",
    "    ax.set_ylim(0, 1)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fa8cfff",
   "metadata": {},
   "source": [
    "### 4.5. Evaluation curves"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5a0b7d21",
   "metadata": {},
   "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>Class</th>\n",
       "      <th>Samples</th>\n",
       "      <th>Correct</th>\n",
       "      <th>Accuracy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-2</td>\n",
       "      <td>60</td>\n",
       "      <td>32</td>\n",
       "      <td>53.3%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-1</td>\n",
       "      <td>678</td>\n",
       "      <td>414</td>\n",
       "      <td>61.1%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>2591</td>\n",
       "      <td>1305</td>\n",
       "      <td>50.4%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2563</td>\n",
       "      <td>1132</td>\n",
       "      <td>44.2%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>202</td>\n",
       "      <td>128</td>\n",
       "      <td>63.4%</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Overall</td>\n",
       "      <td>6094</td>\n",
       "      <td>3011</td>\n",
       "      <td>49.4%</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Class  Samples  Correct Accuracy\n",
       "0       -2       60       32    53.3%\n",
       "1       -1      678      414    61.1%\n",
       "2        0     2591     1305    50.4%\n",
       "3        1     2563     1132    44.2%\n",
       "4        2      202      128    63.4%\n",
       "5  Overall     6094     3011    49.4%"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Binarize labels for multiclass ROC/PR\n",
    "y_test_bin = label_binarize(y_test, classes=range(n_classes))\n",
    "\n",
    "# Compute ROC and PR curves for each class\n",
    "fig, axes = plt.subplots(1, 2, figsize=(10, 4))\n",
    "\n",
    "# ROC curves\n",
    "ax_roc = axes[0]\n",
    "\n",
    "for i, class_name in enumerate(class_names):\n",
    "    fpr, tpr, _ = roc_curve(y_test_bin[:, i], y_prob[:, i])\n",
    "    roc_auc = auc(fpr, tpr)\n",
    "    ax_roc.plot(fpr, tpr, label=f'Class {class_name} (AUC={roc_auc:.2f})')\n",
    "\n",
    "ax_roc.plot([0, 1], [0, 1], 'k--', alpha=0.5)\n",
    "ax_roc.set_xlabel('False positive rate')\n",
    "ax_roc.set_ylabel('True positive rate')\n",
    "ax_roc.set_title('ROC curves (one-vs-rest)')\n",
    "ax_roc.legend(loc='lower right')\n",
    "ax_roc.set_xlim([0, 1])\n",
    "ax_roc.set_ylim([0, 1.05])\n",
    "\n",
    "# PR curves\n",
    "ax_pr = axes[1]\n",
    "\n",
    "for i, class_name in enumerate(class_names):\n",
    "    precision, recall, _ = precision_recall_curve(y_test_bin[:, i], y_prob[:, i])\n",
    "    pr_auc = auc(recall, precision)\n",
    "    ax_pr.plot(recall, precision, label=f'Class {class_name} (AUC={pr_auc:.2f})')\n",
    "\n",
    "ax_pr.set_xlabel('Recall')\n",
    "ax_pr.set_ylabel('Precision')\n",
    "ax_pr.set_title('Precision-recall curves (one-vs-rest)')\n",
    "ax_pr.legend(loc='lower left')\n",
    "ax_pr.set_xlim([0, 1])\n",
    "ax_pr.set_ylim([0, 1.05])\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a59b2536",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "## 5. Activity: Build a CNN-RNN hybrid model\n",
    "\n",
    "Now it's your turn! Modify the model architecture to include **convolutional layers** before the recurrent layers.\n",
    "\n",
    "### Why add convolutions?\n",
    "\n",
    "- **Local pattern detection**: Conv1D layers can detect n-gram patterns (e.g., \"not good\", \"very happy\") that are important for sentiment\n",
    "- **Dimensionality reduction**: Convolutions can reduce sequence length before the RNN, making training faster\n",
    "- **Feature extraction**: The CNN extracts local features, then the RNN captures long-range dependencies\n",
    "\n",
    "### Hints\n",
    "\n",
    "1. **Import the layers you'll need** - look at `tensorflow.keras.layers` for `Conv1D`, `MaxPooling1D`, or `GlobalMaxPooling1D`\n",
    "\n",
    "2. **Where to add convolutions** - think about the data flow:\n",
    "   ```\n",
    "   Embedding → ??? → GRU → Dense\n",
    "   ```\n",
    "   \n",
    "3. **Conv1D parameters to consider**:\n",
    "   - `filters`: How many feature detectors? (try 64-128)\n",
    "   - `kernel_size`: What n-gram size? (try 3-5 for trigrams to 5-grams)\n",
    "   - `activation`: What activation function works well with text?\n",
    "   - `padding`: Should the output be the same length as input?\n",
    "\n",
    "4. **Pooling options**:\n",
    "   - `MaxPooling1D(pool_size=2)`: Reduces sequence length by half\n",
    "   - `GlobalMaxPooling1D()`: Collapses to a single vector (use this if you want to skip the RNN entirely for comparison)\n",
    "\n",
    "5. **Architecture ideas to try**:\n",
    "   - Single conv layer before the GRU\n",
    "   - Multiple conv layers with increasing filter sizes\n",
    "   - Parallel conv layers with different kernel sizes (requires Functional API)\n",
    "\n",
    "### Your task\n",
    "\n",
    "In the cell below, build your CNN-RNN model. Start simple and iterate!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff1c7488",
   "metadata": {},
   "outputs": [],
   "source": [
    "# TODO: Import any additional layers you need\n",
    "from tensorflow.keras.layers import Conv1D  # Add more imports as needed\n",
    "\n",
    "# TODO: Build your CNN-RNN model\n",
    "# Hint: Start with the same structure as the baseline, then add conv layers\n",
    "\n",
    "cnn_rnn_model = Sequential([\n",
    "    Embedding(\n",
    "        vocab_size, \n",
    "        embedding_dim,\n",
    "        weights=[embedding_matrix],\n",
    "        trainable=True\n",
    "    ),\n",
    "    SpatialDropout1D(dropout),\n",
    "    \n",
    "    # TODO: Add your convolutional layer(s) here\n",
    "    # Conv1D(filters=???, kernel_size=???, activation=???, padding=???),\n",
    "    \n",
    "    # Keep or modify the recurrent layers\n",
    "    Bidirectional(GRU(hidden_dim, recurrent_dropout=recurrent_dropout, return_sequences=True)),\n",
    "    Bidirectional(GRU(hidden_dim // 2, recurrent_dropout=recurrent_dropout)),\n",
    "    \n",
    "    Dropout(dropout),\n",
    "    Dense(output_dim, activation='softmax', kernel_regularizer=l2(l2_reg))\n",
    "])\n",
    "\n",
    "cnn_rnn_model.compile(\n",
    "    optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),\n",
    "    loss='sparse_categorical_crossentropy',\n",
    "    metrics=['accuracy']\n",
    ")\n",
    "\n",
    "cnn_rnn_model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d4dfef75",
   "metadata": {},
   "source": [
    "### 5.1. Train your CNN-RNN model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "35d2245e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define callbacks for CNN-RNN model (saves to different file)\n",
    "cnn_rnn_callbacks = [\n",
    "    ModelCheckpoint(\n",
    "        '../models/cnn_rnn_classifier.keras',\n",
    "        save_best_only=True,\n",
    "        monitor='val_accuracy',\n",
    "        verbose=1\n",
    "    ),\n",
    "    EarlyStopping(\n",
    "        monitor='val_loss',\n",
    "        patience=5,\n",
    "        restore_best_weights=True,\n",
    "        verbose=1\n",
    "    )\n",
    "]\n",
    "\n",
    "# Train the CNN-RNN model\n",
    "cnn_rnn_history = cnn_rnn_model.fit(\n",
    "    X_train, y_train,\n",
    "    validation_data=(X_test, y_test),\n",
    "    epochs=30,\n",
    "    batch_size=64,\n",
    "    class_weight=class_weight_dict,\n",
    "    callbacks=cnn_rnn_callbacks\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7951f272",
   "metadata": {},
   "source": [
    "### 5.2. Evaluate your CNN-RNN model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3bc6b841",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load best CNN-RNN model and get predictions\n",
    "cnn_rnn_model = tf.keras.models.load_model('../models/cnn_rnn_classifier.keras')\n",
    "\n",
    "# Get predicted probabilities and classes\n",
    "y_prob_cnn = cnn_rnn_model.predict(X_test)\n",
    "y_pred_cnn = y_prob_cnn.argmax(axis=1)\n",
    "\n",
    "# Calculate accuracy\n",
    "cnn_rnn_accuracy = (y_pred_cnn == y_test).mean()\n",
    "print(f'CNN-RNN model accuracy: {cnn_rnn_accuracy:.1%}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5dee91fe",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "## 6. Compare models\n",
    "\n",
    "Now let's compare your CNN-RNN model to the baseline GRU model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "03720dce",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load both models\n",
    "baseline_model = tf.keras.models.load_model('../models/rnn_classifier.keras')\n",
    "cnn_rnn_model = tf.keras.models.load_model('../models/cnn_rnn_classifier.keras')\n",
    "\n",
    "# Get predictions from both models\n",
    "y_pred_baseline = baseline_model.predict(X_test).argmax(axis=1)\n",
    "y_pred_cnn_rnn = cnn_rnn_model.predict(X_test).argmax(axis=1)\n",
    "\n",
    "# Calculate overall accuracy\n",
    "baseline_acc = (y_pred_baseline == y_test).mean()\n",
    "cnn_rnn_acc = (y_pred_cnn_rnn == y_test).mean()\n",
    "\n",
    "# Create comparison dataframe\n",
    "comparison = pd.DataFrame({\n",
    "    'Model': ['Baseline GRU', 'CNN-RNN'],\n",
    "    'Accuracy': [f'{baseline_acc:.1%}', f'{cnn_rnn_acc:.1%}'],\n",
    "    'Parameters': [baseline_model.count_params(), cnn_rnn_model.count_params()]\n",
    "})\n",
    "\n",
    "print('Model comparison:')\n",
    "comparison"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "53cf2d4d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Side-by-side confusion matrices\n",
    "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
    "\n",
    "for ax, y_pred, title in zip(\n",
    "    axes, \n",
    "    [y_pred_baseline, y_pred_cnn_rnn], \n",
    "    ['Baseline GRU', 'CNN-RNN']\n",
    "):\n",
    "    cm = confusion_matrix(y_test, y_pred)\n",
    "    sns.heatmap(\n",
    "        cm, annot=True, fmt='d', cmap='Blues',\n",
    "        xticklabels=class_names, yticklabels=class_names, ax=ax\n",
    "    )\n",
    "    ax.set_title(f'{title} (Acc: {(y_pred == y_test).mean():.1%})')\n",
    "    ax.set_xlabel('Predicted')\n",
    "    ax.set_ylabel('Actual')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d87f777",
   "metadata": {},
   "source": [
    "## 7. Reflection\n",
    "\n",
    "Answer the following questions:\n",
    "\n",
    "1. **Did your CNN-RNN model outperform the baseline?** Why or why not?\n",
    "\n",
    "2. **How did the number of parameters change?** Is there a trade-off between model complexity and performance?\n",
    "\n",
    "3. **Which classes improved the most?** Look at the per-class accuracy changes.\n",
    "\n",
    "4. **What other architectures could you try?** Consider:\n",
    "   - Multiple conv layers with different kernel sizes\n",
    "   - Using only CNN (no RNN) with GlobalMaxPooling\n",
    "   - LSTM instead of GRU\n",
    "   - Attention mechanisms"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d23f8d6",
   "metadata": {},
   "source": [
    "### Your notes\n",
    "\n",
    "*Write your observations and answers here...*"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}