init commit

model_uploader.ipynb

@@ -0,0 +1,27 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import huggingface_hub as hb\n",
+    "from tensorflow import keras\n",
+    "\n",
+    "# Load the model\n",
+    "model = keras.models.load_model('../../models/imsoumyaneel-sentiment_analysis_llama2.keras')\n",
+    "\n",
+    "# Upload the model to Hugging Face\n",
+    "hub.push_to_hub_keras(model, repo_id=\"yasirfaizahmed/sentiment-text-classifications\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

model_utilizer.ipynb

@@ -0,0 +1,84 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tensorflow.keras.preprocessing.text import Tokenizer\n",
+    "from tensorflow.keras.preprocessing.sequence import pad_sequences\n",
+    "from tensorflow import keras\n",
+    "from pathlib import Path as pp\n",
+    "\n",
+    "import os\n",
+    "notebook_path = os.getcwd()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "File not found: filepath=../imsoumyaneel-sentiment_analysis_llama2.keras. Please ensure the file is an accessible `.keras` zip file.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[19], line 15\u001b[0m\n\u001b[1;32m     12\u001b[0m   \u001b[38;5;28;01mreturn\u001b[39;00m padded_text\n\u001b[1;32m     14\u001b[0m \u001b[38;5;66;03m# load model\u001b[39;00m\n\u001b[0;32m---> 15\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mkeras\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodels\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_model\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43m../imsoumyaneel-sentiment_analysis_llama2.keras\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# Replace \"your_model.h5\" with the path to your trained model\u001b[39;00m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;66;03m# Preprocess the custom input text\u001b[39;00m\n\u001b[1;32m     18\u001b[0m preprocessed_text \u001b[38;5;241m=\u001b[39m preprocess_text(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mi love this thing!\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m~/Documents/models/twitter_model/.venv/lib/python3.10/site-packages/keras/src/saving/saving_api.py:185\u001b[0m, in \u001b[0;36mload_model\u001b[0;34m(filepath, custom_objects, compile, safe_mode)\u001b[0m\n\u001b[1;32m    183\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m legacy_h5_format\u001b[38;5;241m.\u001b[39mload_model_from_hdf5(filepath)\n\u001b[1;32m    184\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(filepath)\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.keras\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m--> 185\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    186\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile not found: filepath=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilepath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    187\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease ensure the file is an accessible `.keras` \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    188\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mzip file.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    189\u001b[0m     )\n\u001b[1;32m    190\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    191\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    192\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFile format not supported: filepath=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfilepath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    193\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mKeras 3 only supports V3 `.keras` files and \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    202\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmight have a different name).\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    203\u001b[0m     )\n",
+      "\u001b[0;31mValueError\u001b[0m: File not found: filepath=../imsoumyaneel-sentiment_analysis_llama2.keras. Please ensure the file is an accessible `.keras` zip file."
+     ]
+    }
+   ],
+   "source": [
+    "tokenizer = Tokenizer()\n",
+    "max_length = 200\n",
+    "models_dir = pp(pp(notebook_path).parent, 'models')\n",
+    "\n",
+    "\n",
+    "# use model\n",
+    "def preprocess_text(text):\n",
+    "  # Tokenize the text\n",
+    "  tokenized_text = tokenizer.texts_to_sequences([text])\n",
+    "  # Pad sequences to the same length as training data\n",
+    "  padded_text = pad_sequences(tokenized_text, maxlen=max_length, padding='post')\n",
+    "  return padded_text\n",
+    "\n",
+    "# load model\n",
+    "model = keras.models.load_model('../imsoumyaneel-sentiment_analysis_llama2.keras')  # Replace \"your_model.h5\" with the path to your trained model\n",
+    "\n",
+    "# Preprocess the custom input text\n",
+    "preprocessed_text = preprocess_text(\"i love this thing!\")\n",
+    "\n",
+    "# Make predictions\n",
+    "predictions = model.predict(preprocessed_text)\n",
+    "\n",
+    "predictions[0][0]"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": 2
+}

notes/mnist.ipynb

@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "b2d6f096-6123-4dd0-ae4f-c9abf70889c4",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-03T17:21:13.044450Z",
+     "iopub.status.busy": "2024-04-03T17:21:13.043912Z",
+     "iopub.status.idle": "2024-04-03T17:21:13.374087Z",
+     "shell.execute_reply": "2024-04-03T17:21:13.373277Z",
+     "shell.execute_reply.started": "2024-04-03T17:21:13.044419Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Reusing dataset mnist (/root/.cache/huggingface/datasets/mnist/mnist/1.0.0/fda16c03c4ecfb13f165ba7e29cf38129ce035011519968cdaf74894ce91c9d4)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "cd2dd3c8b22b49718b3c66585ca3559c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/2 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset\n",
+    "\n",
+    "dataset = load_dataset(\"mnist\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "7c5ea43d-6a70-4deb-a90e-1d7758c961a3",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-03T17:21:27.628082Z",
+     "iopub.status.busy": "2024-04-03T17:21:27.627048Z",
+     "iopub.status.idle": "2024-04-03T17:21:27.632687Z",
+     "shell.execute_reply": "2024-04-03T17:21:27.632002Z",
+     "shell.execute_reply.started": "2024-04-03T17:21:27.628051Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from PIL import Image\n",
+    "import io\n",
+    "\n",
+    "def convert(byte_like_str_image):\n",
+    "    return np.asarray(Image.open(io.BytesIO(byte_like_str_image['bytes'])))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "daafde17-8100-4f49-b27e-8aad43b129c6",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-03T17:22:20.343090Z",
+     "iopub.status.busy": "2024-04-03T17:22:20.341876Z",
+     "iopub.status.idle": "2024-04-03T17:22:27.888815Z",
+     "shell.execute_reply": "2024-04-03T17:22:27.887812Z",
+     "shell.execute_reply.started": "2024-04-03T17:22:20.343047Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "dataset_train = dataset['train'].to_pandas()\n",
+    "dataset_train['image'] = dataset_train['image'].map(convert)\n",
+    "\n",
+    "dataset_test = dataset['test'].to_pandas()\n",
+    "dataset_test['image'] = dataset_test['image'].map(convert)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "72022fd2-000d-4d5c-88d5-9afc62c283d5",
+   "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": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}