From 3b82f51d7377357d59367d34220e5bf591fbf05e Mon Sep 17 00:00:00 2001
From: Jean-Luc Parouty <Jean-Luc.Parouty@grenoble-inp.fr>
Date: Thu, 23 Jan 2020 18:22:59 +0100
Subject: [PATCH] Add BHPD example, another classic one :-)
---
BHPD/01-DNN-Regression.ipynb | 310 ++++++++++++++++++++++++++++++
BHPD/fidle/__init__.py | 2 +
BHPD/fidle/pwk.py | 244 +++++++++++++++++++++++
BHPD/fidle/talk.mplstyle | 33 ++++
GTSRB/02-First-convolutions.ipynb | 14 +-
MNIST/01-DNN-MNIST.ipynb | 4 +-
MNIST/fidle/pwk.py | 3 +-
7 files changed, 599 insertions(+), 11 deletions(-)
create mode 100644 BHPD/01-DNN-Regression.ipynb
create mode 100644 BHPD/fidle/__init__.py
create mode 100644 BHPD/fidle/pwk.py
create mode 100644 BHPD/fidle/talk.mplstyle
diff --git a/BHPD/01-DNN-Regression.ipynb b/BHPD/01-DNN-Regression.ipynb
new file mode 100644
index 0000000..947b95a
--- /dev/null
+++ b/BHPD/01-DNN-Regression.ipynb
@@ -0,0 +1,310 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Deep Neural Network (DNN) - BHPD dataset\n",
+ "========================================\n",
+ "---\n",
+ "Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
+ "\n",
+ "## A very simple example of **regression** :\n",
+ "\n",
+ "Objective is to predicts **housing prices** from a set of house features. \n",
+ "\n",
+ "The **[Boston Housing Dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html)** consists of price of houses in various places in Boston. \n",
+ "Alongside with price, the dataset also provide information such as Crime, areas of non-retail business in the town, \n",
+ "age of people who own the house and many other attributes...\n",
+ "\n",
+ "What we're going to do:\n",
+ "\n",
+ " - Retrieve data\n",
+ " - Preparing the data\n",
+ " - Build a model\n",
+ " - Train the model\n",
+ " - Evaluate the result\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 1/ Init python stuff"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import tensorflow as tf\n",
+ "from tensorflow import keras\n",
+ "\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import pandas as pd\n",
+ "\n",
+ "from IPython.display import display, Markdown\n",
+ "import fidle.pwk as ooo\n",
+ "from importlib import reload\n",
+ "\n",
+ "ooo.init()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 2/ Retrieve data\n",
+ "\n",
+ "**From Keras :**\n",
+ "Boston housing is a famous historic dataset, so we can get it directly from [Keras datasets](https://www.tensorflow.org/api_docs/python/tf/keras/datasets) "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "(x_train, y_train), (x_test, y_test) = keras.datasets.boston_housing.load_data(test_split=0.2, seed=113)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**From a csv file :** \n",
+ "More fun !"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = pd.read_csv('./data/BostonHousing.csv', header=0)\n",
+ "\n",
+ "display(data.head(5).style.format(\"{0:.2f}\"))\n",
+ "print('Données manquantes : ',data.isna().sum().sum(), ' Shape is : ', data.shape)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 3/ Preparing the data\n",
+ "### 3.1/ Split data\n",
+ "We will use 80% of the data for training and 20% for validation. \n",
+ "x will be input data and y the expected output"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Split => train, test\n",
+ "#\n",
+ "data_train = data.sample(frac=0.7, axis=0)\n",
+ "data_test = data.drop(data_train.index)\n",
+ "\n",
+ "# ---- Split => x,y (medv is price)\n",
+ "#\n",
+ "x_train = data_train.drop('medv', axis=1)\n",
+ "y_train = data_train['medv']\n",
+ "x_test = data_test.drop('medv', axis=1)\n",
+ "y_test = data_test['medv']\n",
+ "\n",
+ "print('Original data shape was : ',data.shape)\n",
+ "print('x_train : ',x_train.shape, 'y_train : ',y_train.shape)\n",
+ "print('x_test : ',x_test.shape, 'y_test : ',y_test.shape)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 3.2/ Data normalization\n",
+ "**Note :** \n",
+ " - All input data must be normalized, train and test. \n",
+ " - To do this we will subtract the mean and divide by the standard deviation. \n",
+ " - But test data should not be used in any way, even for normalization. \n",
+ " - The mean and the standard deviation will therefore only be calculated with the train data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
+ "\n",
+ "mean = x_train.mean()\n",
+ "std = x_train.std()\n",
+ "x_train = (x_train - mean) / std\n",
+ "x_test = (x_test - mean) / std\n",
+ "\n",
+ "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"After normalization :\"))\n",
+ "\n",
+ "x_train, y_train = np.array(x_train), np.array(y_train)\n",
+ "x_test, y_test = np.array(x_test), np.array(y_test)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 4/ Build a model\n",
+ "About informations about : \n",
+ " - [Optimizer](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers)\n",
+ " - [Activation](https://www.tensorflow.org/api_docs/python/tf/keras/activations)\n",
+ " - [Loss](https://www.tensorflow.org/api_docs/python/tf/keras/losses)\n",
+ " - [Metrics](https://www.tensorflow.org/api_docs/python/tf/keras/metrics)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ " def get_model_v1(shape):\n",
+ " \n",
+ " model = keras.models.Sequential()\n",
+ " model.add(keras.layers.Dense(64, activation='relu', input_shape=shape))\n",
+ " model.add(keras.layers.Dense(64, activation='relu'))\n",
+ " model.add(keras.layers.Dense(1))\n",
+ " \n",
+ " model.compile(optimizer = 'rmsprop',\n",
+ " loss = 'mse',\n",
+ " metrics = ['mae', 'mse'] )\n",
+ " return model"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 5/ Train the model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model=get_model_v1( (13,) )\n",
+ "\n",
+ "model.summary()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "**Let's go :**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "history = model.fit(x_train,\n",
+ " y_train,\n",
+ " epochs = 100,\n",
+ " batch_size = 10,\n",
+ " verbose = 1,\n",
+ " validation_data = (x_test, y_test))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 6/ Evaluate\n",
+ "### 6.1/ Model evaluation\n",
+ "MAE = Mean Absolute Error (between the labels and predictions) \n",
+ "A mae equal to 3 represents an average error in prediction of $3k."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "score = model.evaluate(x_test, y_test, verbose=0)\n",
+ "\n",
+ "print('x_test / loss : {:5.4f}'.format(score[0]))\n",
+ "print('x_test / mae : {:5.4f}'.format(score[1]))\n",
+ "print('x_test / mse : {:5.4f}'.format(score[2]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 6.2/ Training history\n",
+ "What was the best result during our training ?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "reload(ooo)\n",
+ "ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
+ " 'MAE' :['mae', 'val_mae'],\n",
+ " 'LOSS':['loss','val_loss']})"
+ ]
+ },
+ {
+ "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": "3.7.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/BHPD/fidle/__init__.py b/BHPD/fidle/__init__.py
new file mode 100644
index 0000000..098c126
--- /dev/null
+++ b/BHPD/fidle/__init__.py
@@ -0,0 +1,2 @@
+
+VERSION='0.1a'
\ No newline at end of file
diff --git a/BHPD/fidle/pwk.py b/BHPD/fidle/pwk.py
new file mode 100644
index 0000000..f3aa42f
--- /dev/null
+++ b/BHPD/fidle/pwk.py
@@ -0,0 +1,244 @@
+
+# ==================================================================
+# ____ _ _ _ __ __ _
+# | _ \ _ __ __ _ ___| |_(_) ___ __ _| | \ \ / /__ _ __| | __
+# | |_) | '__/ _` |/ __| __| |/ __/ _` | | \ \ /\ / / _ \| '__| |/ /
+# | __/| | | (_| | (__| |_| | (_| (_| | | \ V V / (_) | | | <
+# |_| |_| \__,_|\___|\__|_|\___\__,_|_| \_/\_/ \___/|_| |_|\_\
+# module pwk
+# ==================================================================
+# A simple module to host some common functions for practical work
+# pjluc 2020
+
+import os
+import glob
+from datetime import datetime
+import itertools
+import datetime, time
+
+import math
+import numpy as np
+
+import tensorflow as tf
+from tensorflow import keras
+
+import matplotlib
+import matplotlib.pyplot as plt
+import seaborn as sn
+
+VERSION='0.1.8'
+
+
+# -------------------------------------------------------------
+# init_all
+# -------------------------------------------------------------
+#
+def init(mplstyle='fidle/talk.mplstyle'):
+ global VERSION
+ # ---- matplotlib
+ matplotlib.style.use(mplstyle)
+ # ---- Hello world
+# now = datetime.datetime.now()
+ print('IDLE 2020 - Practical Work Module')
+ print(' Version :', VERSION)
+ print(' Run time : {}'.format(time.strftime("%A %-d %B %Y, %H:%M:%S")))
+ print(' Matplotlib style :', mplstyle)
+ print(' TensorFlow version :',tf.__version__)
+ print(' Keras version :',tf.keras.__version__)
+
+# -------------------------------------------------------------
+# Folder cooking
+# -------------------------------------------------------------
+#
+def tag_now():
+ return datetime.datetime.now().strftime("%Y-%m-%d_%Hh%Mm%Ss")
+
+def mkdir(path):
+ os.makedirs(path, mode=0o750, exist_ok=True)
+
+def get_directory_size(path):
+ """
+ Return the directory size, but only 1 level
+ args:
+ path : directory path
+ return:
+ size in Mo
+ """
+ size=0
+ for f in os.listdir(path):
+ if os.path.isfile(path+'/'+f):
+ size+=os.path.getsize(path+'/'+f)
+ return size/(1024*1024)
+
+# -------------------------------------------------------------
+# shuffle_dataset
+# -------------------------------------------------------------
+#
+def shuffle_np_dataset(x, y):
+ assert (len(x) == len(y)), "x and y must have same size"
+ p = np.random.permutation(len(x))
+ return x[p], y[p]
+
+
+def update_progress(what,i,imax):
+ bar_length = min(40,imax)
+ if (i%int(imax/bar_length))!=0 and i<imax:
+ return
+ progress = float(i/imax)
+ block = int(round(bar_length * progress))
+ endofline = '\r' if progress<1 else '\n'
+ text = "{:16s} [{}] {:>5.1f}% of {}".format( what, "#"*block+"-"*(bar_length-block), progress*100, imax)
+ print(text, end=endofline)
+
+
+# -------------------------------------------------------------
+# show_images
+# -------------------------------------------------------------
+#
+def plot_images(x,y, indices, columns=12, x_size=1, y_size=1, colorbar=False, y_pred=None, cm='binary'):
+ """
+ Show some images in a grid, with legends
+ args:
+ X: images - Shapes must be (-1 lx,ly,1) or (-1 lx,ly,3)
+ y: real classes
+ indices: indices of images to show
+ columns: number of columns (12)
+ x_size,y_size: figure size
+ colorbar: show colorbar (False)
+ y_pred: predicted classes (None)
+ cm: Matplotlib olor map
+ returns:
+ nothing
+ """
+ rows = math.ceil(len(indices)/columns)
+ fig=plt.figure(figsize=(columns*x_size, rows*(y_size+0.35)))
+ n=1
+ errors=0
+ if np.any(y_pred)==None:
+ y_pred=y
+ for i in indices:
+ axs=fig.add_subplot(rows, columns, n)
+ n+=1
+ # ---- Shape is (lx,ly)
+ if len(x[i].shape)==2:
+ xx=x[i]
+ # ---- Shape is (lx,ly,n)
+ if len(x[i].shape)==3:
+ (lx,ly,lz)=x[i].shape
+ if lz==1:
+ xx=x[i].reshape(lx,ly)
+ else:
+ xx=x[i]
+ img=axs.imshow(xx, cmap = cm, interpolation='lanczos')
+ axs.spines['right'].set_visible(True)
+ axs.spines['left'].set_visible(True)
+ axs.spines['top'].set_visible(True)
+ axs.spines['bottom'].set_visible(True)
+ axs.set_yticks([])
+ axs.set_xticks([])
+ if y[i]!=y_pred[i]:
+ axs.set_xlabel('{} ({})'.format(y_pred[i],y[i]))
+ axs.xaxis.label.set_color('red')
+ errors+=1
+ else:
+ axs.set_xlabel(y[i])
+ if colorbar:
+ fig.colorbar(img,orientation="vertical", shrink=0.65)
+ plt.show()
+
+def plot_image(x,cm='binary', figsize=(4,4)):
+ (lx,ly,lz)=x.shape
+ plt.figure(figsize=figsize)
+ if lz==1:
+ plt.imshow(x.reshape(lx,ly), cmap = cm, interpolation='lanczos')
+ else:
+ plt.imshow(x.reshape(lx,ly,lz),cmap = cm, interpolation='lanczos')
+ plt.show()
+
+
+# -------------------------------------------------------------
+# show_history
+# -------------------------------------------------------------
+#
+def plot_history_obsolete(history, figsize=(8,6)):
+ """
+ Show history
+ args:
+ history: history
+ save_as: filename to save or None
+ """
+ # Accuracy
+ plt.figure(figsize=figsize)
+ plt.plot(history.history['accuracy'])
+ plt.plot(history.history['val_accuracy'])
+ plt.title('Model accuracy')
+ plt.ylabel('Accuracy')
+ plt.xlabel('Epoch')
+ plt.legend(['Train', 'Test'], loc='upper left')
+ plt.show()
+
+ # Loss values
+ plt.figure(figsize=figsize)
+ plt.plot(history.history['loss'])
+ plt.plot(history.history['val_loss'])
+ plt.title('Model loss')
+ plt.ylabel('Loss')
+ plt.xlabel('Epoch')
+ plt.legend(['Train', 'Test'], loc='upper left')
+ plt.show()
+
+def plot_history(history, figsize=(8,6),
+ plot={"Accuracy":['accuracy','val_accuracy'], 'Loss':['loss', 'val_loss']}):
+ """
+ Show history
+ args:
+ history: history
+ figsize: fig size
+ plot: list of data to plot
+ """
+ for title,curves in plot.items():
+ plt.figure(figsize=figsize)
+ plt.title(title)
+ plt.ylabel(title)
+ plt.xlabel('Epoch')
+ for c in curves:
+ plt.plot(history.history[c])
+ plt.legend(curves, loc='upper left')
+ plt.show()
+
+
+
+# -------------------------------------------------------------
+# plot_confusion_matrix
+# -------------------------------------------------------------
+#
+def plot_confusion_matrix(cm,
+ title='Confusion matrix',
+ figsize=(12,8),
+ cmap="gist_heat_r",
+ vmin=0,
+ vmax=1,
+ xticks=5,yticks=5):
+ """
+ given a sklearn confusion matrix (cm), make a nice plot
+
+ Args:
+ cm: confusion matrix from sklearn.metrics.confusion_matrix
+ title: the text to display at the top of the matrix
+ figsize: Figure size (12,8)
+ cmap: color map (gist_heat_r)
+ vmi,vmax: Min/max 0 and 1
+
+ """
+
+ accuracy = np.trace(cm) / float(np.sum(cm))
+ misclass = 1 - accuracy
+
+ plt.figure(figsize=figsize)
+ sn.heatmap(cm, linewidths=1, linecolor="#ffffff",square=True,
+ cmap=cmap, xticklabels=xticks, yticklabels=yticks,
+ vmin=vmin,vmax=vmax)
+ plt.ylabel('True label')
+ plt.xlabel('Predicted label\naccuracy={:0.4f}; misclass={:0.4f}'.format(accuracy, misclass))
+
+ plt.show()
diff --git a/BHPD/fidle/talk.mplstyle b/BHPD/fidle/talk.mplstyle
new file mode 100644
index 0000000..edf3fed
--- /dev/null
+++ b/BHPD/fidle/talk.mplstyle
@@ -0,0 +1,33 @@
+
+# See : https://matplotlib.org/users/customizing.html
+
+axes.titlesize : 24
+axes.labelsize : 20
+axes.edgecolor : dimgrey
+axes.labelcolor : dimgrey
+axes.linewidth : 2
+axes.grid : False
+
+axes.prop_cycle : cycler('color', ['steelblue', 'tomato', '2ca02c', 'd62728', '9467bd', '8c564b', 'e377c2', '7f7f7f', 'bcbd22', '17becf'])
+
+lines.linewidth : 3
+lines.markersize : 10
+
+xtick.color : black
+xtick.labelsize : 18
+ytick.color : black
+ytick.labelsize : 18
+
+axes.spines.left : True
+axes.spines.bottom : True
+axes.spines.top : False
+axes.spines.right : False
+
+savefig.dpi : 300 # figure dots per inch or 'figure'
+savefig.facecolor : white # figure facecolor when saving
+savefig.edgecolor : white # figure edgecolor when saving
+savefig.format : svg
+savefig.bbox : tight
+savefig.pad_inches : 0.1
+savefig.transparent : True
+savefig.jpeg_quality: 95
diff --git a/GTSRB/02-First-convolutions.ipynb b/GTSRB/02-First-convolutions.ipynb
index 36c8325..3aa129a 100644
--- a/GTSRB/02-First-convolutions.ipynb
+++ b/GTSRB/02-First-convolutions.ipynb
@@ -228,9 +228,9 @@
"\n",
"model.summary()\n",
"\n",
- "model.compile(optimizer='adam',\n",
- " loss='sparse_categorical_crossentropy',\n",
- " metrics=['accuracy'])"
+ "model.compile(optimizer = 'adam',\n",
+ " loss = 'sparse_categorical_crossentropy',\n",
+ " metrics = ['accuracy'])"
]
},
{
@@ -256,10 +256,10 @@
"\n",
"# ---- Train\n",
"history = model.fit( x_train, y_train,\n",
- " batch_size=batch_size,\n",
- " epochs=epochs,\n",
- " verbose=1,\n",
- " validation_data=(x_test, y_test))"
+ " batch_size = batch_size,\n",
+ " epochs = epochs,\n",
+ " verbose = 1,\n",
+ " validation_data = (x_test, y_test))"
]
},
{
diff --git a/MNIST/01-DNN-MNIST.ipynb b/MNIST/01-DNN-MNIST.ipynb
index 0c7c3d3..cf30ece 100644
--- a/MNIST/01-DNN-MNIST.ipynb
+++ b/MNIST/01-DNN-MNIST.ipynb
@@ -4,12 +4,12 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "Deep Neural Network (DNN) - MNIST Example\n",
+ "Deep Neural Network (DNN) - MNIST dataset\n",
"=========================================\n",
"---\n",
"Introduction au Deep Learning (IDLE) - S. Arias, E. Maldonado, JL. Parouty - CNRS/SARI/DEVLOG - 2020 \n",
"\n",
- "## A very simple example :\n",
+ "## A very simple example of **classification** :\n",
"...but a must-have example, a classic !\n",
"\n",
" - Retrieve data\n",
diff --git a/MNIST/fidle/pwk.py b/MNIST/fidle/pwk.py
index c21924a..fbefd30 100644
--- a/MNIST/fidle/pwk.py
+++ b/MNIST/fidle/pwk.py
@@ -186,8 +186,7 @@ def plot_history(history, figsize=(8,6)):
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()
-
-
+
# -------------------------------------------------------------
# plot_confusion_matrix
# -------------------------------------------------------------
--
GitLab