01.getting-started-with-pytorch changed

CherkNevis.ipynb

@@ -0,0 +1,343 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1733d9de-60ea-46b9-b07e-0036aac64dfa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_data_size = 14\n",
+    "daily_cases = [1,11,3,4,5,6,7,8,9,10,23,4,5,6,7,899,34,8,44,5,657,57,0,5,65,7,6,7]\n",
+    "\n",
+    "train_data = daily_cases[:-test_data_size] # take all elements of daily_cases except the last 14\n",
+    "test_data = daily_cases[-test_data_size:]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "c511900c-20f9-450a-87e4-119cf53935df",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[6, 7, 8, 9, 0]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "listt = [1,2,3,4,5,6,7,8,9,0]\n",
+    "listt[-5:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a8345fec-19ca-4284-a52a-34289e603427",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[1, 11, 3, 4, 5, 6, 7, 8, 9, 10, 23, 4, 5, 6]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# train_data = daily_cases[:-test_data_size]\n",
+    "\n",
+    "train_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c3d7145d-b1d0-45ff-bc08-f5cb444ac99f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original daily_cases:\n",
+      "2024-06-15    100\n",
+      "2024-06-16    150\n",
+      "2024-06-17    200\n",
+      "2024-06-18    300\n",
+      "2024-06-19    400\n",
+      "Freq: D, dtype: int64\n",
+      "2024-06-15      NaN\n",
+      "2024-06-16     50.0\n",
+      "2024-06-17     50.0\n",
+      "2024-06-18    100.0\n",
+      "2024-06-19    100.0\n",
+      "Freq: D, dtype: float64\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "2024-08-02    10\n",
+       "2024-08-03    20\n",
+       "2024-08-04    30\n",
+       "2024-08-05    40\n",
+       "2024-08-06    50\n",
+       "Freq: D, dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Sample cumulative cases Series\n",
+    "import pandas as pd\n",
+    "data = [100, 150, 200, 300, 400]\n",
+    "index = pd.date_range(start='2024-06-15', periods=5)\n",
+    "daily_cases = pd.Series(data, index=index)\n",
+    "\n",
+    "# Original daily_cases (cumulative data)\n",
+    "print(\"Original daily_cases:\")\n",
+    "print(daily_cases)\n",
+    "ss = daily_cases.diff()\n",
+    "print(ss)\n",
+    "my_pandas_series = pd.Series([10,20,30,40,50], index = pd.date_range(start = '2024-08-02', periods = 5))\n",
+    "my_pandas_series\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e0602486-94af-493a-9f5c-f9c0661bcaca",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Transformed daily_cases:\n",
+      "2024-06-15     NaN\n",
+      "2024-06-16   -50.0\n",
+      "2024-06-17     0.0\n",
+      "2024-06-18    50.0\n",
+      "2024-06-19     0.0\n",
+      "Freq: D, dtype: float64\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Apply the transformation\n",
+    "daily_cases = daily_cases.diff()\n",
+    "\n",
+    "# Transformed daily_cases (daily data)\n",
+    "print(\"\\nTransformed daily_cases:\")\n",
+    "print(daily_cases)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "abe21bdd-dc98-4ec9-861a-d7358ed56e65",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "nan"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "\n",
+    "# Example series\n",
+    "daily_cases = pd.Series([10, 20, 15])\n",
+    "\n",
+    "# Step 1: Calculate differences\n",
+    "diff = daily_cases.diff()  # Result: [NaN, 10.0, -5.0]\n",
+    "\n",
+    "# Step 2: Replace NaN with the first element\n",
+    "filled_diff = diff.fillna(daily_cases[0])  # Result: [10.0, 10.0, -5.0]\n",
+    "\n",
+    "# Step 3: Convert to integers\n",
+    "final_result = filled_diff.astype(np.int64)  # Result: [10, 10, -5]\n",
+    "\n",
+    "# Assign back to daily_cases\n",
+    "daily_cases = final_result\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "43880cb4-0fbd-45f2-af33-14d4b4316736",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Scaled Train Data: [0.   0.25 0.5  0.75 1.  ]\n",
+      "Scaled Test Data: [1.25 1.5  1.75 2.   2.25]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "\n",
+    "# Example data\n",
+    "train_data = np.array([10, 20, 30, 40, 50])\n",
+    "test_data = np.array([60, 70, 80, 90, 100])\n",
+    "\n",
+    "# Initialize the scaler\n",
+    "scaler = MinMaxScaler()\n",
+    "\n",
+    "\n",
+    "# Fit the scaler on the training data\n",
+    "scaler = scaler.fit(np.expand_dims(train_data, axis=1))\n",
+    "\n",
+    "# Transform the training data\n",
+    "train_data_scaled = scaler.transform(np.expand_dims(train_data, axis=1))\n",
+    "\n",
+    "# Transform the test data\n",
+    "test_data_scaled = scaler.transform(np.expand_dims(test_data, axis=1))\n",
+    "\n",
+    "# Print results\n",
+    "print(\"Scaled Train Data:\", train_data_scaled.flatten())\n",
+    "print(\"Scaled Test Data:\", test_data_scaled.flatten())\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "6b239718-9dd7-4e58-9657-67e00cbd596f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Scaled Train Data: [[0.  ]\n",
+      " [0.25]\n",
+      " [0.5 ]\n",
+      " [0.75]\n",
+      " [1.  ]]\n",
+      "Scaled Test Data: [[1.25]\n",
+      " [1.5 ]\n",
+      " [1.75]\n",
+      " [2.  ]\n",
+      " [2.25]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Scaled Train Data:\", train_data_scaled)\n",
+    "print(\"Scaled Test Data:\", test_data_scaled)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "23476fd8-6145-4f7d-81f7-adbc4855e452",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'LSTM_model.svg'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torchviz import make_dot\n",
+    "\n",
+    "# Define the LSTM model\n",
+    "class LSTMNet(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size, output_size, n_layers=1):\n",
+    "        super(LSTMNet, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.n_layers = n_layers\n",
+    "        self.lstm = nn.LSTM(input_size, hidden_size, n_layers, batch_first=True)\n",
+    "        self.fc = nn.Linear(hidden_size, output_size)\n",
+    "    \n",
+    "    def forward(self, x):\n",
+    "        h0 = torch.zeros(self.n_layers, x.size(0), self.hidden_size).to(x.device)\n",
+    "        c0 = torch.zeros(self.n_layers, x.size(0), self.hidden_size).to(x.device)\n",
+    "        out, _ = self.lstm(x, (h0, c0))\n",
+    "        out = self.fc(out[:, -1, :])\n",
+    "        return out\n",
+    "\n",
+    "# Hyperparameters\n",
+    "input_size = 1\n",
+    "hidden_size = 50\n",
+    "output_size = 1\n",
+    "num_layers = 1\n",
+    "\n",
+    "# Initialize the model\n",
+    "model = LSTMNet(input_size, hidden_size, output_size, num_layers)\n",
+    "\n",
+    "# Create a dummy input\n",
+    "dummy_input = torch.randn(1, 10, input_size)  # Batch size = 1, Sequence length = 10, Input size = 1\n",
+    "\n",
+    "# Generate the computation graph\n",
+    "output = model(dummy_input)\n",
+    "dot = make_dot(output, params=dict(model.named_parameters()))\n",
+    "dot.format = 'svg'\n",
+    "dot.render(\"LSTM_model\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18b89e50-14a6-4bd1-9841-e876ae2bc983",
+   "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": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

LSTM_model

@@ -0,0 +1,50 @@
+digraph {
+	graph [size="12,12"]
+	node [align=left fontname=monospace fontsize=10 height=0.2 ranksep=0.1 shape=box style=filled]
+	2283802772080 [label="
+ (1, 1)" fillcolor=darkolivegreen1]
+	2283802592880 [label=AddmmBackward0]
+	2283802592688 -> 2283802592880
+	2283802772000 [label="fc.bias
+ (1)" fillcolor=lightblue]
+	2283802772000 -> 2283802592688
+	2283802592688 [label=AccumulateGrad]
+	2283802595280 -> 2283802592880
+	2283802595280 [label=SliceBackward0]
+	2283802593312 -> 2283802595280
+	2283802593312 [label=SelectBackward0]
+	2283802592112 -> 2283802593312
+	2283802592112 [label=SliceBackward0]
+	2283802593504 -> 2283802592112
+	2283802593504 [label=TransposeBackward0]
+	2283802592928 -> 2283802593504
+	2283802592928 [label=MkldnnRnnLayerBackward0]
+	2283802593408 -> 2283802592928
+	2283656326896 [label="lstm.weight_ih_l0
+ (200, 1)" fillcolor=lightblue]
+	2283656326896 -> 2283802593408
+	2283802593408 [label=AccumulateGrad]
+	2283802593744 -> 2283802592928
+	2283656326816 [label="lstm.weight_hh_l0
+ (200, 50)" fillcolor=lightblue]
+	2283656326816 -> 2283802593744
+	2283802593744 [label=AccumulateGrad]
+	2283802593648 -> 2283802592928
+	2283656326976 [label="lstm.bias_ih_l0
+ (200)" fillcolor=lightblue]
+	2283656326976 -> 2283802593648
+	2283802593648 [label=AccumulateGrad]
+	2283802594032 -> 2283802592928
+	2283656327056 [label="lstm.bias_hh_l0
+ (200)" fillcolor=lightblue]
+	2283656327056 -> 2283802594032
+	2283802594032 [label=AccumulateGrad]
+	2283802594992 -> 2283802592880
+	2283802594992 [label=TBackward0]
+	2283802593024 -> 2283802594992
+	2283802771920 [label="fc.weight
+ (1, 50)" fillcolor=lightblue]
+	2283802771920 -> 2283802593024
+	2283802593024 [label=AccumulateGrad]
+	2283802592880 -> 2283802772080
+}