{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Numpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Les opérations sur les matrices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a1 = [1, 2, 3, 4]\n",
    "b1 = [5, 6, 7, 8]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.add(a1,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.subtract(a1,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.multiply(a1,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.multiply(4,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.dot(a1,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c1 = np.dot(5,b1)\n",
    "print(c1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b1 = [5, 6, 7, 8,9]\n",
    "c1 = np.dot(a1,b1)\n",
    "print(c)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a1 = [1, 2]\n",
    "moyen = np.average(a1)\n",
    "print(moyen)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tranposition matricielle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b1 = [[5, 6, 7, 8, 9],\n",
    "      [1, 2, 3, 4, 5]]\n",
    "print(b1)\n",
    "b1 = np.array(b1)\n",
    "print(b1.T)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Séparer une matrice en deux, horizontalement et verticalement"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = [[0, 0, 0],\n",
    "        [0, 1, 0],\n",
    "        [1, 0, 0],\n",
    "        [1, 1, 1]]\n",
    "a = np.array(a)\n",
    "\n",
    "a = np.hsplit(a, [2])\n",
    "\n",
    "a1  = a[0]\n",
    "a2  = a[1]\n",
    "print(a1)\n",
    "print(a2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = [[0, 0, 0],\n",
    "        [0, 1, 0],\n",
    "        [1, 0, 0],\n",
    "        [1, 1, 1]]\n",
    "a = np.array(a)\n",
    "\n",
    "a = np.vsplit(a, [2])\n",
    "\n",
    "a1  = a[0]\n",
    "a2  = a[1]\n",
    "print(a1)\n",
    "print(a2)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Les opérations sur les matrices bidimensionnelles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a2 = [[1, 2, 3, 4],\n",
    "     [1, 2, 3, 4]]\n",
    "b2 = [[5, 6, 7, 8],\n",
    "     [5, 6, 7, 8]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c2 = np.add(a2,b2)\n",
    "print(c2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c2 = np.subtract(a2,b2)\n",
    "print(c2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c2 = np.multiply(a2,b2)\n",
    "print(c2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c2 = np.dot(a2,b2)\n",
    "print(c2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Redéfinir une matrice"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b2.reshape(4,2)\n",
    "print(b2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Créer des matrices avec des nombres aléatoires"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.random.rand()\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.random.rand(1)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.random.rand(2,5)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.random.rand(2,3,3)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.zeros(1)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.zeros(1, dtype=int)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = np.zeros((2,5), dtype=int)\n",
    "print(a)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Quelques fonctions pour travailler avec des listes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = [12, 13, 14, 15]\n",
    "a_reverse = reversed(a)\n",
    "\n",
    "for num in a_reverse:\n",
    "    print(num)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "jours = ['dimanche', 'lundi', 'mardi', 'mercredi', 'jeudi', 'vendredi']\n",
    "jours_num = list(enumerate(jours))\n",
    "print(jours_num)\n",
    "\n",
    "jours_num = list(enumerate(jours, start=1))\n",
    "print(jours_num)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a1 = [1, 2, 3, 4]\n",
    "b1 = [5, 6, 7, 8]\n",
    "\n",
    "zipped = list(zip(a1, b1))\n",
    "print(zipped)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a1 = [1, 2, 3, 4]\n",
    "b1 = [5, 6, 7, 8]\n",
    "\n",
    "ezipped = list(enumerate(zip(a1, b1)))\n",
    "print(ezipped)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Visualisation avec matplotlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import matplotlib.pyplot as plot\n",
    "\n",
    "x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]\n",
    "y = [0, 1, 0, 0, 1, 0, 1, 1, 1, 0]\n",
    "plot.plot(x, y, linewidth=3, drawstyle=\"steps\", color=\"#00363a\")\n",
    "plot.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pandas et Scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plot\n",
    "from sklearn.cluster import KMeans\n",
    "\n",
    "numarray = np.array([[1, 1], [1, 2], [1, 3], [1, 4], [1, 5], \n",
    "              [1, 6], [1, 7], [1, 8],[1, 9], [1, 10], \n",
    "              [10, 1], [10, 2], [10, 3], [10, 4], [10, 5], \n",
    "              [10, 6], [10, 7], [10, 8],[10, 9], [10, 10]])\n",
    "\n",
    "clusters = KMeans(n_clusters = 4, n_init=2)\n",
    "clusters.fit(numarray)\n",
    "colors = np.array([\"#ff0000\", \"#00ff00\", \"#0000ff\", \"#ffff00\"])\n",
    "    \n",
    "plot.scatter(numarray[:, 0], numarray[:, 1], c=colors[clusters.labels_])\n",
    "plot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import datasets, svm\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plot\n",
    "\n",
    "digits = datasets.load_digits()\n",
    "\n",
    "training_images = digits.images[:int(digits.images.shape[0]/2)]\n",
    "training_images = training_images.reshape((training_images.shape[0], -1))\n",
    "\n",
    "training_target = digits.target[0:int(digits.target.shape[0]/2)]\n",
    "\n",
    "classifier = svm.SVC(gamma=0.001, C=100.)\n",
    "# entraînement\n",
    "classifier.fit(training_images, training_target)\n",
    "\n",
    "# prédiction\n",
    "predict_image = digits.images[int(digits.images.shape[0]/2)+2]\n",
    "print(\"Predicted value: \", classifier.predict(predict_image.reshape(1,-1)))\n",
    "\n",
    "plot.imshow(predict_image, cmap=plot.cm.gray_r)\n",
    "plot.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plot\n",
    "import pandas as pd\n",
    "from sklearn.linear_model import LinearRegression\n",
    "dataset = np.loadtxt(\"population.csv\", dtype={'names': ('year', 'population'), 'formats': ('i4', 'i')},\n",
    "    skiprows=1, delimiter=\",\", encoding=\"UTF-8\")\n",
    "\n",
    "df = pd.DataFrame(dataset)\n",
    "\n",
    "# données d'entraînement\n",
    "x_train = df['year'][:40].values.reshape(-1, 1)\n",
    "y_train = df['population'][:40].values.reshape(-1, 1)\n",
    "\n",
    "# entraînement\n",
    "lr = LinearRegression()\n",
    "lr.fit(x_train, y_train)\n",
    "\n",
    "# affichage des coefficients\n",
    "print(lr.intercept_, lr.coef_)\n",
    "\n",
    "# prédiction\n",
    "x_predict = x_train = df['year'][41:].values.reshape(-1, 1)\n",
    "y_actual = df['population'][41:].values.reshape(-1, 1)\n",
    "y_predict = lr.predict(x_predict)\n",
    "\n",
    "plot.scatter(x_predict, y_actual)\n",
    "plot.plot(x_predict, y_predict, color='red', linewidth=2)\n",
    "plot.show()"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}