Added dimensionality red methods

2018-10-24 07:50:56 +02:00
parent 9f00db99f7
commit ec7b073679
13 changed files with 5463 additions and 2 deletions
@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import mglearn\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "from scipy import signal\n",
+    "from sklearn.datasets import load_boston\n",
+    "from sklearn.preprocessing import MinMaxScaler, PolynomialFeatures\n",
+    "from mglearn.make_blobs import make_blobs\n",
+    "\n",
+    "#DATA_PATH = os.path.join(os.path.dirname(__file__), \"data\")\n",
+    "\n",
+    "\n",
+    "def make_forge():\n",
+    "    # a carefully hand-designed dataset lol\n",
+    "    X, y = make_blobs(centers=2, random_state=4, n_samples=30)\n",
+    "    y[np.array([7, 27])] = 0\n",
+    "    mask = np.ones(len(X), dtype=np.bool)\n",
+    "    mask[np.array([0, 1, 5, 26])] = 0\n",
+    "    X, y = X[mask], y[mask]\n",
+    "    return X, y\n",
+    "\n",
+    "\n",
+    "def make_wave(n_samples=100):\n",
+    "    rnd = np.random.RandomState(42)\n",
+    "    x = rnd.uniform(-3, 3, size=n_samples)\n",
+    "    y_no_noise = (np.sin(4 * x) + x)\n",
+    "    y = (y_no_noise + rnd.normal(size=len(x))) / 2\n",
+    "    return x.reshape(-1, 1), y\n",
+    "\n",
+    "\n",
+    "def load_extended_boston():\n",
+    "    boston = load_boston()\n",
+    "    X = boston.data\n",
+    "\n",
+    "    X = MinMaxScaler().fit_transform(boston.data)\n",
+    "    X = PolynomialFeatures(degree=2, include_bias=False).fit_transform(X)\n",
+    "    return X, boston.target\n",
+    "\n",
+    "\n",
+    "def load_citibike():\n",
+    "    data_mine = pd.read_csv(os.path.join(DATA_PATH, \"citibike.csv\"))\n",
+    "    data_mine['one'] = 1\n",
+    "    data_mine['starttime'] = pd.to_datetime(data_mine.starttime)\n",
+    "    data_starttime = data_mine.set_index(\"starttime\")\n",
+    "    data_resampled = data_starttime.resample(\"3h\").sum().fillna(0)\n",
+    "    return data_resampled.one\n",
+    "\n",
+    "\n",
+    "def make_signals():\n",
+    "    # fix a random state seed\n",
+    "    rng = np.random.RandomState(42)\n",
+    "    n_samples = 2000\n",
+    "    time = np.linspace(0, 8, n_samples)\n",
+    "    # create three signals\n",
+    "    s1 = np.sin(2 * time)  # Signal 1 : sinusoidal signal\n",
+    "    s2 = np.sign(np.sin(3 * time))  # Signal 2 : square signal\n",
+    "    s3 = signal.sawtooth(2 * np.pi * time)  # Signal 3: saw tooth signal\n",
+    "\n",
+    "    # concatenate the signals, add noise\n",
+    "    S = np.c_[s1, s2, s3]\n",
+    "    S += 0.2 * rng.normal(size=S.shape)\n",
+    "\n",
+    "    S /= S.std(axis=0)  # Standardize data\n",
+    "    S -= S.min()\n",
+    "    return S\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "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": "3.7.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}