noshot 0.1.7__py3-none-any.whl → 0.1.9__py3-none-any.whl

noshot/data/ML TS XAI/NLP/NLP 6/7. PCFG using CYK.ipynb

@@ -1,383 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "b624a9ba-0ae8-4c87-ae4c-476684d7e101",
-   "metadata": {},
-   "source": [
-    "# Implement Probabilistic Context Free Grammar (PCFG) and find the inside probability of a word sequence using the CYK algorithm."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "a0748f9b-182a-42ac-847e-265497da12ad",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "Enter the number of rules :  12\n",
-      "TAG 1 :  S\n",
-      "RULE :  NP VP\n",
-      "PROPABILITY :  1.0\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 2 :  PP\n",
-      "RULE :  P NP\n",
-      "PROPABILITY :  1.0\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 3 :  VP\n",
-      "RULE :  V NP\n",
-      "PROPABILITY :  0.7\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 4 :  VP\n",
-      "RULE :  VP PP\n",
-      "PROPABILITY :  0.3\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 5 :  P\n",
-      "RULE :  WITH\n",
-      "PROPABILITY :  1.0\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 6 :  V\n",
-      "RULE :  SAW\n",
-      "PROPABILITY :  1.0\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 7 :  NP\n",
-      "RULE :  NP PP\n",
-      "PROPABILITY :  0.4\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 8 :  NP\n",
-      "RULE :  ASTRONOMERS\n",
-      "PROPABILITY :  0.1\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 9 :  NP\n",
-      "RULE :  EARS\n",
-      "PROPABILITY :  0.18\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 10 :  NP\n",
-      "RULE :  SAW\n",
-      "PROPABILITY :  0.04\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 11 :  NP\n",
-      "RULE :  STARS\n",
-      "PROPABILITY :  0.18\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "TAG 12 :  NP\n",
-      "RULE :  TELESCOPE\n",
-      "PROPABILITY :  0.1\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "num = int(input(\"Enter the number of rules : \"))\n",
-    "PCFG = {}\n",
-    "for i in range(num) :\n",
-    "    tag = input(f\"TAG {i+1} : \").upper()\n",
-    "    rule = input(f\"RULE : \").upper()\n",
-    "    prop = float(input(f\"PROPABILITY : \"))\n",
-    "    print()\n",
-    "    if tag in PCFG :\n",
-    "        PCFG[tag].append((rule, prop))\n",
-    "    else :\n",
-    "        PCFG[tag] = [(rule, prop)]\n",
-    "    "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "f811e0cd-554c-4149-ab46-4ee4abe8150d",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "Enter the Word Sequence :  ASTRONOMERS SAW STARS WITH EARS\n"
-     ]
-    }
-   ],
-   "source": [
-    "word_seq = input(\"Enter the Word Sequence : \").upper().split(' ')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "id": "803ea9fe-2905-4fc2-aafb-75156645b579",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def CYK(word_seq, PCFG) :\n",
-    "    PI = [[{} for _ in range(len(word_seq))] for _ in range(len(word_seq))]\n",
-    "    BOOK = [[{} for _ in range(len(word_seq))] for _ in range(len(word_seq))]\n",
-    "    for i in range(len(word_seq)) :\n",
-    "        for tag, rule_list in PCFG.items() :\n",
-    "            for rule, prop in rule_list :\n",
-    "                if rule == word_seq[i] :\n",
-    "                    PI[i][i][tag] = prop\n",
-    "                    BOOK[i][i][tag] = word_seq[i]\n",
-    "                \n",
-    "\n",
-    "    l = len(word_seq)\n",
-    "    for c in range(1, l) :\n",
-    "        for i in range(0, l-c) :\n",
-    "            j = i + c\n",
-    "            for m in range(i, j) :\n",
-    "                for rule1 in PI[i][m] :\n",
-    "                    for rule2 in PI[m+1][j] :\n",
-    "                        entry = rule1 + \" \" + rule2\n",
-    "                        for tag, rule_list in PCFG.items() :\n",
-    "                            for rule, prop in rule_list :\n",
-    "                                if rule == entry :\n",
-    "                                    val = prop*PI[i][m][rule1]*PI[m+1][j][rule2]\n",
-    "                                    if tag in PI[i][j] :\n",
-    "                                        PI[i][j][tag] += val\n",
-    "                                        BOOK[i][j][tag] += [(rule, m)]\n",
-    "                                    else :\n",
-    "                                        PI[i][j][tag] = val\n",
-    "                                        BOOK[i][j][tag] = [(rule, m)]\n",
-    "\n",
-    "    return PI, BOOK\n",
-    "                    \n",
-    "                \n",
-    "                "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "id": "d52f8d91-260c-49c8-a63e-f378f8dd5698",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[{'NP': 0.1}, {}, {'S': 0.0126}, {}, {'S': 0.0015875999999999998}]\n",
-      "[{}, {'V': 1.0, 'NP': 0.04}, {'VP': 0.126}, {}, {'VP': 0.015875999999999998}]\n",
-      "[{}, {}, {'NP': 0.18}, {}, {'NP': 0.01296}]\n",
-      "[{}, {}, {}, {'P': 1.0}, {'PP': 0.18}]\n",
-      "[{}, {}, {}, {}, {'NP': 0.18}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "PI, BOOK = CYK(word_seq, PCFG)\n",
-    "for row in PI :\n",
-    "    print(row)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "id": "7ec3e635-9e33-469f-975b-88d0c6236ddb",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Propability of the given word sequence : {'S': 0.0015875999999999998}\n"
-     ]
-    }
-   ],
-   "source": [
-    "n = len(word_seq)\n",
-    "print(f\"Propability of the given word sequence : {PI[0][n-1]}\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "07c3e3d9-70be-433c-be83-97d004c258d9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[{'NP': 'ASTRONOMERS'}, {}, {'S': [('NP VP', 0)]}, {}, {'S': [('NP VP', 0)]}]\n",
-      "[{}, {'V': 'SAW', 'NP': 'SAW'}, {'VP': [('V NP', 1)]}, {}, {'VP': [('V NP', 1), ('VP PP', 2)]}]\n",
-      "[{}, {}, {'NP': 'STARS'}, {}, {'NP': [('NP PP', 2)]}]\n",
-      "[{}, {}, {}, {'P': 'WITH'}, {'PP': [('P NP', 3)]}]\n",
-      "[{}, {}, {}, {}, {'NP': 'EARS'}]\n"
-     ]
-    }
-   ],
-   "source": [
-    "for row in BOOK :\n",
-    "    print(row)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a92dbc9f-1e5b-4370-9f73-5105f09b89d7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

noshot/data/ML TS XAI/NLP/NLP 6/8. BOW and TF-IDF.ipynb

@@ -1,252 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "a5300496-5a71-44c4-968a-df705d3b87dd",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer\n",
-    "from sklearn.preprocessing import LabelEncoder\n",
-    "import tensorflow as tf\n",
-    "from tensorflow.keras import Sequential\n",
-    "from tensorflow.keras.layers import Dense"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "bb5c905b-ee46-474c-b994-2dc9cfd39d39",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = {'text': ['I love programming', 'Python is great', 'I enjoy machine learning',\n",
-    "                 'TensorFlow is a powerful tool', 'AI is the future'],\n",
-    "        'label': ['positive', 'positive', 'positive', 'positive', 'neutral']}\n",
-    "df = pd.DataFrame(data)\n",
-    "labelencoder = LabelEncoder()\n",
-    "df['label'] = labelencoder.fit_transform(df['label'])\n",
-    "x_train,x_test,y_train,y_test = train_test_split(df['text'],df['label'],test_size=0.2,random_state=42)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "cf62ab92-aae6-487c-a39d-dcbd9faa0b39",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Training with Bag of words\n",
-      "Epoch 1/10\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\BHARATH.K\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\keras\\src\\layers\\core\\dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",
-      "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 12ms/step - accuracy: 0.1667 - loss: 0.7754  \n",
-      "Epoch 2/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.1667 - loss: 0.7541     \n",
-      "Epoch 3/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.7022 \n",
-      "Epoch 4/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.6927 \n",
-      "Epoch 5/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.6833 \n",
-      "Epoch 6/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.1667 - loss: 0.7077     \n",
-      "Epoch 7/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.3333 - loss: 0.6650 \n",
-      "Epoch 8/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.5000 - loss: 0.6935 \n",
-      "Epoch 9/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.3333 - loss: 0.6888     \n",
-      "Epoch 10/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.5000 - loss: 0.6398 \n",
-      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 195ms/step - accuracy: 0.0000e+00 - loss: 0.8297\n",
-      "BOW model accuracy:0.0\n",
-      "Training with TF-IDF\n",
-      "Epoch 1/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 5ms/step - accuracy: 0.3333 - loss: 0.7194\n",
-      "Epoch 2/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.6764 \n",
-      "Epoch 3/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - accuracy: 0.1667 - loss: 0.7094     \n",
-      "Epoch 4/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.5000 - loss: 0.7018 \n",
-      "Epoch 5/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.6667 - loss: 0.6567 \n",
-      "Epoch 6/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.5000 - loss: 0.7085 \n",
-      "Epoch 7/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.5000 - loss: 0.6754 \n",
-      "Epoch 8/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.3333 - loss: 0.7031     \n",
-      "Epoch 9/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 6ms/step - accuracy: 0.6667 - loss: 0.6347 \n",
-      "Epoch 10/10\n",
-      "\u001b[1m2/2\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 7ms/step - accuracy: 0.5000 - loss: 0.6415 \n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "<keras.src.callbacks.history.History at 0x1d2600a15b0>"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "vectorizer_bow = CountVectorizer()\n",
-    "x_train_bow = vectorizer_bow.fit_transform(x_train).toarray()\n",
-    "x_test_bow = vectorizer_bow.transform(x_test).toarray()\n",
-    "\n",
-    "vectorizer_tfidf = TfidfVectorizer()\n",
-    "x_train_tfidf = vectorizer_tfidf.fit_transform(x_train).toarray()\n",
-    "x_test_tfidf = vectorizer_tfidf.transform(x_test).toarray()\n",
-    "\n",
-    "def build_model(input_dim):\n",
-    "    model = Sequential()\n",
-    "    model.add(Dense(16,activation='relu',input_dim=input_dim))\n",
-    "    model.add(Dense(8,activation='relu'))\n",
-    "    model.add(Dense(1,activation='sigmoid'))\n",
-    "    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])\n",
-    "    return model\n",
-    "\n",
-    "print(\"Training with Bag of words\")\n",
-    "model_bow = build_model(x_train_bow.shape[1])\n",
-    "model_bow.fit(x_train_bow,y_train,epochs=10,batch_size=2,verbose=1)\n",
-    "loss,accuracy = model_bow.evaluate(x_test_bow,y_test)\n",
-    "\n",
-    "print(f\"BOW model accuracy:{accuracy}\")\n",
-    "\n",
-    "print(\"Training with TF-IDF\")\n",
-    "model_tfidf = build_model(x_train_tfidf.shape[1])\n",
-    "model_tfidf.fit(x_train_tfidf,y_train,epochs=10,batch_size=2,verbose=1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "8dd3cb94-1fef-46a5-aeba-21ab61a92310",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step\n",
-      "BOW predictions: [[0.50319755]\n",
-      " [0.4361956 ]\n",
-      " [0.5179436 ]\n",
-      " [0.4758614 ]\n",
-      " [0.40164202]]\n",
-      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step\n",
-      "TF-IDF predictions: [[0.5335882 ]\n",
-      " [0.5208615 ]\n",
-      " [0.49639997]\n",
-      " [0.46454915]\n",
-      " [0.4026386 ]]\n"
-     ]
-    }
-   ],
-   "source": [
-    "data_bow = vectorizer_bow.transform(data['text']).toarray()\n",
-    "data_bow_predictions = model_bow.predict(data_bow)\n",
-    "print(\"BOW predictions:\",data_bow_predictions)\n",
-    "\n",
-    "data_tfidf = vectorizer_tfidf.transform(data['text']).toarray()\n",
-    "data_tfidf_predictions = model_tfidf.predict(data_tfidf)\n",
-    "print(\"TF-IDF predictions:\",data_tfidf_predictions)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "8b8826c3-0e4e-4e42-932a-3656c6895bd9",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['positive', 'neutral', 'positive', 'neutral', 'neutral']\n"
-     ]
-    }
-   ],
-   "source": [
-    "                                threshold=0.5\n",
-    "predictions_bow_label =['positive' if p >= threshold else 'neutral' for p in data_bow_predictions] \n",
-    "print(predictions_bow_label)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "bcf2ea5a-9100-4263-b9de-cec80f97700b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['positive', 'positive', 'neutral', 'neutral', 'neutral']\n"
-     ]
-    }
-   ],
-   "source": [
-    "predictions_tfidf_label =['positive' if p >= threshold else 'neutral' for p in data_tfidf_predictions] \n",
-    "print(predictions_tfidf_label)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "40d4fc45-068e-46d3-9362-6f2c754f21a3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}