pandasで円グラフ作成
pandasでpltは直接できて便利
defaulte_fig_size = plt.rcParams["figure.figsize"] plt.rcParams["figure.figsize"] = [12.0, 10.0] # plt.figure() # fig, axes = plt.subplots(nrows=4, ncols=1, ) fig = plt.figure() ax1 = fig.add_subplot(221) ax1.title.set_text('all member') df_all_cluster[["count_cluster"]].plot(kind='pie', subplots=True, title='all member', ax=ax1, legend=False) ax2 = fig.add_subplot(222) df_2[["count_cluster"]].plot(kind='pie', subplots=True, title='ax2', ax=ax2, legend=False) ax2.title.set_text('ax2') ax3 = fig.add_subplot(223) df_3[["count_cluster"]].plot(kind='pie', subplots=True,title='ax3', ax=ax3, legend=False) ax3.title.set_text('ax3') ax4 = fig.add_subplot(224) df_4[["count_cluster"]].plot(kind='pie', subplots=True, title='ax4', ax=ax4, legend=False) ax4.title.set_text('ax4') plt.savefig('cluster.png', dpi=None) plt.show() plt.rcParams["figure.figsize"] = defaulte_fig_size plt.close('all')
以下でも良いかも。
fig, axes = plt.subplots(nrows=4, ncols=1, figsize=(12, 10)) # 左上 ax[0, 0].plot(x, y1) # 右上 ax[0, 1].plot(x, y2) # 左下 ax[1, 0].plot(x, y3) # 右下 ax[1, 1].plot(x, y4)
tensflow で CNN を試す
CNN のチュートリアルをやってみた。 画像以外でも使いたい。
import numpy as np import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) train_data = mnist.train.images # Returns np.array train_labels = np.asarray(mnist.train.labels, dtype=np.int32) eval_data = mnist.test.images # Returns np.array eval_labels = np.asarray(mnist.test.labels, dtype=np.int32) ## cnn_model_fn から、EstimatorのSpecを受け、分類器の作成 mnist_classifier = tf.estimator.Estimator( model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model") ## 進行状況のログ tensors_to_log = {"probabilities": "softmax_tensor"} logging_hook = tf.train.LoggingTensorHook( tensors=tensors_to_log, every_n_iter=50) ## トレーニング train_input_fn = tf.estimator.inputs.numpy_input_fn( x={"x": train_data}, y=train_labels, batch_size=100, num_epochs=None, shuffle=True) mnist_classifier.train( input_fn=train_input_fn, steps=20000, hooks=[logging_hook]) ## テスト eval_input_fn = tf.estimator.inputs.numpy_input_fn( x={"x": eval_data}, y=eval_labels, num_epochs=1, shuffle=False) eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn) print(eval_results)
def cnn_model_fn(features, labels, mode): """Model function for CNN.""" # Input Layer input_layer = tf.reshape(features["x"], [-1, 28, 28, 1]) # Convolutional Layer #1 conv1 = tf.layers.conv2d( inputs=input_layer, filters=32, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) # Pooling Layer #1 pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2) # Convolutional Layer #2 and Pooling Layer #2 conv2 = tf.layers.conv2d( inputs=pool1, filters=64, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2) # Dense Layer pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64]) dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu) dropout = tf.layers.dropout( inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN) # Logits Layer logits = tf.layers.dense(inputs=dropout, units=10) predictions = { # Generate predictions (for PREDICT and EVAL mode) "classes": tf.argmax(input=logits, axis=1), # Add `softmax_tensor` to the graph. It is used for PREDICT and by the # `logging_hook`. "probabilities": tf.nn.softmax(logits, name="softmax_tensor") } if mode == tf.estimator.ModeKeys.PREDICT: return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions) # Calculate Loss (for both TRAIN and EVAL modes) loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits) # Configure the Training Op (for TRAIN mode) if mode == tf.estimator.ModeKeys.TRAIN: optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001) train_op = optimizer.minimize( loss=loss, global_step=tf.train.get_global_step()) return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op) # Add evaluation metrics (for EVAL mode) eval_metric_ops = { "accuracy": tf.metrics.accuracy( labels=labels, predictions=predictions["classes"])} return tf.estimator.EstimatorSpec( mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)
Build a Convolutional Neural Network using Estimators | TensorFlow
データの増加(ずらしたり、ズームしたり、、)
逆はしない。6と9の問題があるので
# With data augmentation to prevent overfitting (accuracy 0.99286) datagen = ImageDataGenerator( featurewise_center=False, # set input mean to 0 over the dataset samplewise_center=False, # set each sample mean to 0 featurewise_std_normalization=False, # divide inputs by std of the dataset samplewise_std_normalization=False, # divide each input by its std zca_whitening=False, # apply ZCA whitening rotation_range=10, # randomly rotate images in the range (degrees, 0 to 180) zoom_range = 0.1, # Randomly zoom image width_shift_range=0.1, # randomly shift images horizontally (fraction of total width) height_shift_range=0.1, # randomly shift images vertically (fraction of total height) horizontal_flip=False, # randomly flip images vertical_flip=False) # randomly flip images datagen.fit(X_train)
Confusion Matrixの作成(True Label と Predicted Label)
# Look at confusion matrix def plot_confusion_matrix(cm, classes, normalize=False, title='Confusion matrix', cmap=plt.cm.Blues): """ This function prints and plots the confusion matrix. Normalization can be applied by setting `normalize=True`. """ plt.imshow(cm, interpolation='nearest', cmap=cmap) plt.title(title) plt.colorbar() tick_marks = np.arange(len(classes)) plt.xticks(tick_marks, classes, rotation=45) plt.yticks(tick_marks, classes) if normalize: cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis] thresh = cm.max() / 2. for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])): plt.text(j, i, cm[i, j], horizontalalignment="center", color="white" if cm[i, j] > thresh else "black") plt.tight_layout() plt.ylabel('True label') plt.xlabel('Predicted label') # Predict the values from the validation dataset Y_pred = model.predict(X_val) # Convert predictions classes to one hot vectors Y_pred_classes = np.argmax(Y_pred,axis = 1) # Convert validation observations to one hot vectors Y_true = np.argmax(Y_val,axis = 1) # compute the confusion matrix confusion_mtx = confusion_matrix(Y_true, Y_pred_classes) # plot the confusion matrix plot_confusion_matrix(confusion_mtx, classes = range(10))
誤判定の画像抽出
# Display some error results # Errors are difference between predicted labels and true labels errors = (Y_pred_classes - Y_true != 0) Y_pred_classes_errors = Y_pred_classes[errors] Y_pred_errors = Y_pred[errors] Y_true_errors = Y_true[errors] X_val_errors = X_val[errors] def display_errors(errors_index,img_errors,pred_errors, obs_errors): """ This function shows 6 images with their predicted and real labels""" n = 0 nrows = 2 ncols = 3 fig, ax = plt.subplots(nrows,ncols,sharex=True,sharey=True) for row in range(nrows): for col in range(ncols): error = errors_index[n] ax[row,col].imshow((img_errors[error]).reshape((28,28))) ax[row,col].set_title("Predicted label :{}\nTrue label :{}".format(pred_errors[error],obs_errors[error])) n += 1 # Probabilities of the wrong predicted numbers Y_pred_errors_prob = np.max(Y_pred_errors,axis = 1) # Predicted probabilities of the true values in the error set true_prob_errors = np.diagonal(np.take(Y_pred_errors, Y_true_errors, axis=1)) # Difference between the probability of the predicted label and the true label delta_pred_true_errors = Y_pred_errors_prob - true_prob_errors # Sorted list of the delta prob errors sorted_dela_errors = np.argsort(delta_pred_true_errors) # Top 6 errors most_important_errors = sorted_dela_errors[-6:] # Show the top 6 errors display_errors(most_important_errors, X_val_errors, Y_pred_classes_errors, Y_true_errors)
matplotlib で figureの大きさを変える方法
import math import numpy as np from matplotlib import pyplot fig = pyplot.figure(figsize=(12, 4)) pi = math.pi #mathモジュールのπを利用 x = np.linspace(0, 2*pi, 100) #0から2πまでの範囲を100分割したnumpy配列 y = np.sin(x) # adjustFigAspect(fig,aspect=.5) ax = fig.add_subplot(111) ax.plot(range(10),range(10))
def adjustFigAspect(fig,aspect=1): ''' Adjust the subplot parameters so that the figure has the correct aspect ratio. ''' xsize,ysize = fig.get_size_inches() minsize = min(xsize,ysize) xlim = .4*minsize/xsize ylim = .4*minsize/ysize if aspect < 1: xlim *= aspect else: ylim /= aspect fig.subplots_adjust(left=.5-xlim, right=.5+xlim, bottom=.5-ylim, top=.5+ylim)
こんな感じにデフォルト設定を変えるのもあり
defaulte_fig_size = plt.rcParams["figure.figsize"] plt.rcParams["figure.figsize"] = [6.0, 18.0] ... plt.tight_layout() plt.show() plt.rcParams["figure.figsize"] = defaulte_fig_size
silhouette_samples が Memory Errorになったときの対応
from sklearn.metrics import silhouette_samples
silhouette_samples で、Memory Error にならない関数を作ってくれている。
matplotlibについて
matplotlib について、一回tutorial やったほうが良いかも
sshできる local serverのIPに辺りをつける。
nmap で 探す
sudo nmap -sS -p 22 --open 192.168.33.0/24 ## 権限の変更を使った。 sudo chown -R $(whoami) /usr/local/Homebrew