![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "OBJETIVO= Diseñar un pipeline completo para abordar una tarea de Procesamiento de Lenguaje Natural (NLP) usando un dataset real.\n"
+ ],
+ "metadata": {
+ "id": "_OVV8SxT9qIb"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "⚡️ Problema elegido: clasificación binaria de sentimiento a partir de texto."
+ ],
+ "metadata": {
+ "id": "r-MJIcuh-KT1"
+ }
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "id": "80HgIo-Z63VO"
+ },
+ "outputs": [],
+ "source": [
+ "import re\n",
+ "import io\n",
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "\n",
+ "from google.colab import files\n",
+ "\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.metrics import classification_report, confusion_matrix, f1_score, roc_curve, auc\n",
+ "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "\n",
+ "import matplotlib.pyplot as plt\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import kagglehub\n",
+ "\n",
+ "# Download latest version\n",
+ "path = kagglehub.dataset_download(\"sonalshinde123/whatsapp-user-reviews-dataset\")\n",
+ "\n",
+ "print(\"Path to dataset files:\", path)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "_VWBZMUj7LE-",
+ "outputId": "a8ce3022-6a7b-4689-d53d-e38717847f84"
+ },
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Warning: Looks like you're using an outdated `kagglehub` version (installed: 0.3.13), please consider upgrading to the latest version (1.0.0).\n",
+ "Downloading from https://www.kaggle.com/api/v1/datasets/download/sonalshinde123/whatsapp-user-reviews-dataset?dataset_version_number=1...\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "100%|██████████| 313k/313k [00:00<00:00, 56.1MB/s]"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Extracting files...\n",
+ "Path to dataset files: /root/.cache/kagglehub/datasets/sonalshinde123/whatsapp-user-reviews-dataset/versions/1\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import os\n",
+ "import glob\n",
+ "\n",
+ "\n",
+ "csv_files = glob.glob(os.path.join(path, '*.csv'))\n",
+ "\n",
+ "if csv_files:\n",
+ " file_to_load = csv_files[0]\n",
+ " df = pd.read_csv(file_to_load)\n",
+ " print(f\"Loaded dataframe from: {file_to_load}\")\n",
+ " df.head()\n",
+ "else:\n",
+ " print(f\"No CSV files found in the directory: {path}\")\n",
+ " df = None #"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "qPq4ndNI7SSE",
+ "outputId": "13aeca73-21b7-4d08-8341-20d74c670236"
+ },
+ "execution_count": 5,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Loaded dataframe from: /root/.cache/kagglehub/datasets/sonalshinde123/whatsapp-user-reviews-dataset/versions/1/whatsapp_reviews.csv\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "print(\"Shape inicial:\", df.shape)\n",
+ "\n",
+ "print(\"\\nValores nulos por columna:\")\n",
+ "print(df.isna().sum())\n",
+ "\n",
+ "print(\"\\nCantidad de filas duplicadas:\", df.duplicated().sum())\n",
+ "\n",
+ "df = df.drop_duplicates()\n",
+ "print(\"\\nShape luego de drop_duplicates:\", df.shape)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "tpfxKuMI7j0I",
+ "outputId": "635a7742-d8f6-4423-fcca-ca5a625903fb"
+ },
+ "execution_count": 6,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Shape inicial: (5400, 5)\n",
+ "\n",
+ "Valores nulos por columna:\n",
+ "review_id 0\n",
+ "rating 0\n",
+ "review_text 0\n",
+ "review_date 0\n",
+ "helpful 0\n",
+ "dtype: int64\n",
+ "\n",
+ "Cantidad de filas duplicadas: 0\n",
+ "\n",
+ "Shape luego de drop_duplicates: (5400, 5)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "CALIDAD DE DATOS"
+ ],
+ "metadata": {
+ "id": "t2BsoG8G7nZO"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "# Clasificación binaria:\n",
+ "# Positivo (1): rating >= 4\n",
+ "# Negativo (0): rating <= 2\n",
+ "# Eliminamos rating == 3 (neutral) para reducir ambigüedad en un problema binario\n",
+ "\n",
+ "LABEL_COL = 'rating' # Define LABEL_COL\n",
+ "df = df[df[LABEL_COL] != 3].copy()\n",
+ "df[\"label\"] = (df[LABEL_COL] >= 4).astype(int)\n",
+ "\n",
+ "LABEL_FINAL = \"label\"\n",
+ "print(df[LABEL_FINAL].value_counts(normalize=True))"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "SwCtiMI77qFE",
+ "outputId": "fff0267d-e248-4d1d-a218-9ccbc19568b6"
+ },
+ "execution_count": 8,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "label\n",
+ "1 0.655663\n",
+ "0 0.344337\n",
+ "Name: proportion, dtype: float64\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "LABEL_FINAL = 'label'"
+ ],
+ "metadata": {
+ "id": "lZn_kotm8Bwi"
+ },
+ "execution_count": 15,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "EDA"
+ ],
+ "metadata": {
+ "id": "oPwmXQsO8Gs6"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "TEXT_COL = 'review_text'\n",
+ "df[\"text_raw\"] = df[TEXT_COL].astype(str)\n",
+ "df[\"char_len\"] = df[\"text_raw\"].str.len()\n",
+ "df[\"word_len\"] = df[\"text_raw\"].str.split().apply(len)\n",
+ "\n",
+ "print(df[[\"char_len\",\"word_len\"]].describe())\n",
+ "\n",
+ "plt.hist(df[\"word_len\"], bins=50)\n",
+ "plt.title(\"Distribución de longitud (palabras)\")\n",
+ "plt.xlabel(\"Cantidad de palabras\")\n",
+ "plt.ylabel(\"Frecuencia\")\n",
+ "plt.show()\n",
+ "\n",
+ "print(\"Balance de clases:\\n\", df[LABEL_FINAL].value_counts())"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 758
+ },
+ "id": "6wmZPX2I8Eei",
+ "outputId": "4dc3f1f0-1e30-4c98-86a4-78587eb34ef8"
+ },
+ "execution_count": 11,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ " char_len word_len\n",
+ "count 5059.000000 5059.000000\n",
+ "mean 71.786914 13.432892\n",
+ "std 90.196712 16.289104\n",
+ "min 3.000000 1.000000\n",
+ "25% 19.000000 4.000000\n",
+ "50% 37.000000 7.000000\n",
+ "75% 83.000000 16.000000\n",
+ "max 500.000000 105.000000\n"
+ ]
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "| \n", + " | text_raw | \n", + "text_clean | \n", + "
|---|---|---|
| 0 | \n", + "Great 👍 | \n", + "great | \n", + "
| 1 | \n", + "plz whats up unban | \n", + "plz whats up unban | \n", + "
| 2 | \n", + "my contact didn't show on WhatsApp .. for priv... | \n", + "my contact didn t show on whatsapp for privacy... | \n", + "
| 3 | \n", + "Can you guys let archived group chats stay arc... | \n", + "can you guys let archived group chats stay arc... | \n", + "
| 4 | \n", + "it is the g.o.a.t🇿🇼 | \n", + "it is the g o a t | \n", + "
| \n", + " | text | \n", + "y_true | \n", + "y_pred | \n", + "prob_pos | \n", + "
|---|---|---|---|---|
| 498 | \n", + "good great reliable awesome and above all easy... | \n", + "0 | \n", + "1 | \n", + "0.991205 | \n", + "
| 285 | \n", + "nice chatting | \n", + "0 | \n", + "1 | \n", + "0.985454 | \n", + "
| 246 | \n", + "l like this app and l rate five star | \n", + "0 | \n", + "1 | \n", + "0.974760 | \n", + "
| 27 | \n", + "good app | \n", + "0 | \n", + "1 | \n", + "0.956187 | \n", + "
| 488 | \n", + "important features missing shedule messages us... | \n", + "0 | \n", + "1 | \n", + "0.954421 | \n", + "
| 29 | \n", + "a good app | \n", + "0 | \n", + "1 | \n", + "0.946731 | \n", + "
| 126 | \n", + "its my life | \n", + "0 | \n", + "1 | \n", + "0.946695 | \n", + "
| 70 | \n", + "this app really works for communication and so... | \n", + "0 | \n", + "1 | \n", + "0.944390 | \n", + "
| 382 | \n", + "arratai is best | \n", + "0 | \n", + "1 | \n", + "0.934909 | \n", + "
| 544 | \n", + "really useful but it becomes more and more ful... | \n", + "0 | \n", + "1 | \n", + "0.934733 | \n", + "
| \n", + " | order_id | \n", + "fecha | \n", + "order_customer_id | \n", + "product_id | \n", + "unit_price | \n", + "quantity | \n", + "price | \n", + "product_family | \n", + "latitude | \n", + "longitude | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1016330781887 | \n", + "2023-05-29 | \n", + "6451824076 | \n", + "IAM925P00XXZPUDIA | \n", + "19.0 | \n", + "8 | \n", + "152.0 | \n", + "Pulsera | \n", + "37.788617 | \n", + "-3.790215 | \n", + "
| 1 | \n", + "1095376438463 | \n", + "2023-07-16 | \n", + "664062345899 | \n", + "OTS925P00XXZPUDOT | \n", + "19.0 | \n", + "6 | \n", + "114.0 | \n", + "Pulsera | \n", + "40.299542 | \n", + "-3.926774 | \n", + "
| 2 | \n", + "1047641588927 | \n", + "2023-06-17 | \n", + "642133246635 | \n", + "UND925P00XXZCOMUN | \n", + "25.0 | \n", + "5 | \n", + "125.0 | \n", + "Collar | \n", + "39.651927 | \n", + "-0.411277 | \n", + "
| 3 | \n", + "1181322118257 | \n", + "2023-08-29 | \n", + "714672128644 | \n", + "OTS925A00XXZPUDOT | \n", + "19.0 | \n", + "4 | \n", + "76.0 | \n", + "Pulsera | \n", + "39.456511 | \n", + "-0.346203 | \n", + "
| 4 | \n", + "1017492866239 | \n", + "2023-05-30 | \n", + "196440539724 | \n", + "IMO925P00XXZTOMIM | \n", + "25.0 | \n", + "3 | \n", + "75.0 | \n", + "Tobillera | \n", + "37.394171 | \n", + "-5.957857 | \n", + "
| 5 | \n", + "480728843265 | \n", + "2023-03-27 | \n", + "226613674572 | \n", + "UDL925P00XXVPUSUD | \n", + "25.0 | \n", + "3 | \n", + "75.0 | \n", + "Pulsera | \n", + "38.984944 | \n", + "-3.927849 | \n", + "
| 6 | \n", + "457358836737 | \n", + "2023-03-10 | \n", + "244904182348 | \n", + "UND925P00XXZCOMUN | \n", + "25.0 | \n", + "3 | \n", + "75.0 | \n", + "Collar | \n", + "40.604510 | \n", + "-4.339488 | \n", + "
| 7 | \n", + "1001207956671 | \n", + "2023-05-21 | \n", + "621451002539 | \n", + "OTS925P00XXZTODOT | \n", + "19.0 | \n", + "3 | \n", + "57.0 | \n", + "Tobillera | \n", + "40.804126 | \n", + "0.516218 | \n", + "
| 8 | \n", + "1057963181247 | \n", + "2023-06-23 | \n", + "647359906475 | \n", + "UND925P00XXZCOMUN | \n", + "25.0 | \n", + "3 | \n", + "75.0 | \n", + "Collar | \n", + "41.361692 | \n", + "2.129037 | \n", + "
| 9 | \n", + "1095376438463 | \n", + "2023-07-16 | \n", + "664062345899 | \n", + "OTS925P00XXZPUDOT | \n", + "19.0 | \n", + "3 | \n", + "57.0 | \n", + "Pulsera | \n", + "40.299542 | \n", + "-3.926774 | \n", + "
| \n", + " | fecha | \n", + "price | \n", + "ventas_dia_anterior | \n", + "
|---|---|---|---|
| 0 | \n", + "2023-03-03 | \n", + "436.0 | \n", + "NaN | \n", + "
| 1 | \n", + "2023-03-04 | \n", + "372.0 | \n", + "436.0 | \n", + "
| 2 | \n", + "2023-03-05 | \n", + "75.0 | \n", + "372.0 | \n", + "
| 3 | \n", + "2023-03-06 | \n", + "723.0 | \n", + "75.0 | \n", + "
| 4 | \n", + "2023-03-07 | \n", + "732.0 | \n", + "723.0 | \n", + "
| \n", + " | survived | \n", + "pclass | \n", + "sex | \n", + "age | \n", + "sibsp | \n", + "parch | \n", + "fare | \n", + "embarked | \n", + "class | \n", + "who | \n", + "adult_male | \n", + "deck | \n", + "embark_town | \n", + "alive | \n", + "alone | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "0 | \n", + "3 | \n", + "male | \n", + "22.0 | \n", + "1 | \n", + "0 | \n", + "7.2500 | \n", + "S | \n", + "Third | \n", + "man | \n", + "True | \n", + "NaN | \n", + "Southampton | \n", + "no | \n", + "False | \n", + "
| 1 | \n", + "1 | \n", + "1 | \n", + "female | \n", + "38.0 | \n", + "1 | \n", + "0 | \n", + "71.2833 | \n", + "C | \n", + "First | \n", + "woman | \n", + "False | \n", + "C | \n", + "Cherbourg | \n", + "yes | \n", + "False | \n", + "
| 2 | \n", + "1 | \n", + "3 | \n", + "female | \n", + "26.0 | \n", + "0 | \n", + "0 | \n", + "7.9250 | \n", + "S | \n", + "Third | \n", + "woman | \n", + "False | \n", + "NaN | \n", + "Southampton | \n", + "yes | \n", + "True | \n", + "
| 3 | \n", + "1 | \n", + "1 | \n", + "female | \n", + "35.0 | \n", + "1 | \n", + "0 | \n", + "53.1000 | \n", + "S | \n", + "First | \n", + "woman | \n", + "False | \n", + "C | \n", + "Southampton | \n", + "yes | \n", + "False | \n", + "
| 4 | \n", + "0 | \n", + "3 | \n", + "male | \n", + "35.0 | \n", + "0 | \n", + "0 | \n", + "8.0500 | \n", + "S | \n", + "Third | \n", + "man | \n", + "True | \n", + "NaN | \n", + "Southampton | \n", + "no | \n", + "True | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 886 | \n", + "0 | \n", + "2 | \n", + "male | \n", + "27.0 | \n", + "0 | \n", + "0 | \n", + "13.0000 | \n", + "S | \n", + "Second | \n", + "man | \n", + "True | \n", + "NaN | \n", + "Southampton | \n", + "no | \n", + "True | \n", + "
| 887 | \n", + "1 | \n", + "1 | \n", + "female | \n", + "19.0 | \n", + "0 | \n", + "0 | \n", + "30.0000 | \n", + "S | \n", + "First | \n", + "woman | \n", + "False | \n", + "B | \n", + "Southampton | \n", + "yes | \n", + "True | \n", + "
| 888 | \n", + "0 | \n", + "3 | \n", + "female | \n", + "NaN | \n", + "1 | \n", + "2 | \n", + "23.4500 | \n", + "S | \n", + "Third | \n", + "woman | \n", + "False | \n", + "NaN | \n", + "Southampton | \n", + "no | \n", + "False | \n", + "
| 889 | \n", + "1 | \n", + "1 | \n", + "male | \n", + "26.0 | \n", + "0 | \n", + "0 | \n", + "30.0000 | \n", + "C | \n", + "First | \n", + "man | \n", + "True | \n", + "C | \n", + "Cherbourg | \n", + "yes | \n", + "True | \n", + "
| 890 | \n", + "0 | \n", + "3 | \n", + "male | \n", + "32.0 | \n", + "0 | \n", + "0 | \n", + "7.7500 | \n", + "Q | \n", + "Third | \n", + "man | \n", + "True | \n", + "NaN | \n", + "Queenstown | \n", + "no | \n", + "True | \n", + "
891 rows × 15 columns
\n", + "| \n", + " | survived | \n", + "pclass | \n", + "age | \n", + "sibsp | \n", + "parch | \n", + "fare | \n", + "
|---|---|---|---|---|---|---|
| count | \n", + "891.000000 | \n", + "891.000000 | \n", + "714.000000 | \n", + "891.000000 | \n", + "891.000000 | \n", + "891.000000 | \n", + "
| mean | \n", + "0.383838 | \n", + "2.308642 | \n", + "29.699118 | \n", + "0.523008 | \n", + "0.381594 | \n", + "32.204208 | \n", + "
| std | \n", + "0.486592 | \n", + "0.836071 | \n", + "14.526497 | \n", + "1.102743 | \n", + "0.806057 | \n", + "49.693429 | \n", + "
| min | \n", + "0.000000 | \n", + "1.000000 | \n", + "0.420000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "
| 25% | \n", + "0.000000 | \n", + "2.000000 | \n", + "20.125000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "7.910400 | \n", + "
| 50% | \n", + "0.000000 | \n", + "3.000000 | \n", + "28.000000 | \n", + "0.000000 | \n", + "0.000000 | \n", + "14.454200 | \n", + "
| 75% | \n", + "1.000000 | \n", + "3.000000 | \n", + "38.000000 | \n", + "1.000000 | \n", + "0.000000 | \n", + "31.000000 | \n", + "
| max | \n", + "1.000000 | \n", + "3.000000 | \n", + "80.000000 | \n", + "8.000000 | \n", + "6.000000 | \n", + "512.329200 | \n", + "
| \n", + " | count | \n", + "sum | \n", + "mean | \n", + "
|---|---|---|---|
| pclass | \n", + "\n", + " | \n", + " | \n", + " |
| 1 | \n", + "216 | \n", + "136 | \n", + "0.629630 | \n", + "
| 2 | \n", + "184 | \n", + "87 | \n", + "0.472826 | \n", + "
| 3 | \n", + "491 | \n", + "119 | \n", + "0.242363 | \n", + "
| \n", + " | count | \n", + "sum | \n", + "mean | \n", + "
|---|---|---|---|
| sex | \n", + "\n", + " | \n", + " | \n", + " |
| female | \n", + "314 | \n", + "233 | \n", + "0.742038 | \n", + "
| male | \n", + "577 | \n", + "109 | \n", + "0.188908 | \n", + "
| \n", + " | count | \n", + "sum | \n", + "mean | \n", + "
|---|---|---|---|
| embark_town | \n", + "\n", + " | \n", + " | \n", + " |
| Cherbourg | \n", + "168 | \n", + "93 | \n", + "0.553571 | \n", + "
| Queenstown | \n", + "77 | \n", + "30 | \n", + "0.389610 | \n", + "
| Southampton | \n", + "644 | \n", + "217 | \n", + "0.336957 | \n", + "