Feat: Boilerplate for timeseries dataset

- Added a practice file Signed-off-by: Arkadip <[email protected]>
darkmatter18 · Feb 17, 2020 · 4c75cf8 · 4c75cf8
1 parent 65963e6
commit 4c75cf8
Show file tree

Hide file tree

Showing 4 changed files with 2,465 additions and 186 deletions.
diff --git a/Untitled.ipynb b/Untitled.ipynb
@@ -0,0 +1,266 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from preprocessing import Normalize_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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>time</th>\n",
+       "      <th>air_temperature_mean</th>\n",
+       "      <th>pressure</th>\n",
+       "      <th>wind_direction</th>\n",
+       "      <th>wind_speed</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.370203</td>\n",
+       "      <td>0.103164</td>\n",
+       "      <td>0.732591</td>\n",
+       "      <td>0.625000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>0.000011</td>\n",
+       "      <td>0.322799</td>\n",
+       "      <td>0.268912</td>\n",
+       "      <td>0.838440</td>\n",
+       "      <td>0.354167</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>0.000022</td>\n",
+       "      <td>0.302483</td>\n",
+       "      <td>0.709078</td>\n",
+       "      <td>0.988858</td>\n",
+       "      <td>0.260417</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3</td>\n",
+       "      <td>0.000033</td>\n",
+       "      <td>0.246050</td>\n",
+       "      <td>0.850758</td>\n",
+       "      <td>0.239554</td>\n",
+       "      <td>0.093750</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4</td>\n",
+       "      <td>0.000044</td>\n",
+       "      <td>0.194131</td>\n",
+       "      <td>0.827372</td>\n",
+       "      <td>0.345404</td>\n",
+       "      <td>0.291667</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       time  air_temperature_mean  pressure  wind_direction  wind_speed\n",
+       "0  0.000000              0.370203  0.103164        0.732591    0.625000\n",
+       "1  0.000011              0.322799  0.268912        0.838440    0.354167\n",
+       "2  0.000022              0.302483  0.709078        0.988858    0.260417\n",
+       "3  0.000033              0.246050  0.850758        0.239554    0.093750\n",
+       "4  0.000044              0.194131  0.827372        0.345404    0.291667"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset = Normalize_df(pd.read_csv('./dataset-daily.csv'))\n",
+    "dataset.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0       0.000000\n",
+       "1       0.000011\n",
+       "2       0.000022\n",
+       "3       0.000033\n",
+       "4       0.000044\n",
+       "          ...   \n",
+       "3648    0.999956\n",
+       "3649    0.999967\n",
+       "3650    0.999978\n",
+       "3651    0.999989\n",
+       "3652    1.000000\n",
+       "Name: time, Length: 3653, dtype: float64"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset.pop('time')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "z = np.zeros((6,4))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in range(6):\n",
+    "    z[i,:] = dataset.iloc[i].to_numpy()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0.37020316, 0.10316374, 0.73259053, 0.62500003],\n",
+       "       [0.3227991 , 0.26891239, 0.83844011, 0.35416667],\n",
+       "       [0.30248307, 0.70907824, 0.98885794, 0.26041667],\n",
+       "       [0.24604966, 0.85075755, 0.23955432, 0.09375   ],\n",
+       "       [0.19413093, 0.82737157, 0.3454039 , 0.29166667],\n",
+       "       [0.16704289, 0.66712609, 0.33983287, 0.23958333]])"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "z"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "t = torch.from_numpy(z)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[0.3702, 0.1032, 0.7326, 0.6250],\n",
+       "        [0.3228, 0.2689, 0.8384, 0.3542],\n",
+       "        [0.3025, 0.7091, 0.9889, 0.2604],\n",
+       "        [0.2460, 0.8508, 0.2396, 0.0938],\n",
+       "        [0.1941, 0.8274, 0.3454, 0.2917],\n",
+       "        [0.1670, 0.6671, 0.3398, 0.2396]])"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "t.type(torch.FloatTensor)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}