def vis_square(data):
"""
Code from: http://nbviewer.jupyter.org/github/BVLC/caffe/blob/master/examples/00-classification.ipynb, with small modifications
Take an array of shape (n, height, width) or (n, height, width, 3)
and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)
"""
# normalize data for display
data = (data - data.min()) / (data.max() - data.min())
# force the number of filters to be square
n = int(np.ceil(np.sqrt(data.shape[0])))
padding = (((0, n**2 - data.shape[0]), (0, 1),
(0, 1)) + ((0, 0), ) * (data.ndim - 3)
) # don't pad the last dimension (if there is one)
data = np.pad(data, padding, mode='constant',
constant_values=1) # pad with ones (white)
# tile the filters into an image
data = data.reshape((n, n) + data.shape[1:]).transpose(
(0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))
data = data.reshape((n * data.shape[1], n * data.shape[3]) +
data.shape[4:])
fig = plt.figure(figsize=(10, 10))
ax = fig.add_subplot(111)
with plt.rc_context({
'image.interpolation': 'nearest',
'image.cmap': 'gray'
}):
ax.imshow(data)
ax.axis('off')
return fig
def show_training_matrixes(estimates, title):
length = len(estimates)
axes = []
fig = plt.figure(figsize=(100, 2 * length))
fig.suptitle(title, fontsize=30, verticalalignment='top')
for i in range(length):
axes.append(fig.add_subplot(length, 1, i + 1))
with plt.rc_context({'image.cmap': 'gray', 'image.interpolation': 'nearest'}):
for i in range(length):
axes[i].matshow(estimates[i])
axes[i].axis('off')
return fig
# %tensorflow_version 2.x
import tensorflow as tf
import tensorflow_hub as hub
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Embedding, Flatten, GlobalAveragePooling1D
import numpy as np
import pandas as pd
import matplotlib.pylab as plt
import os, re, json, functools
plt.rc_context({'xtick.color':'w', 'ytick.color':'w', 'text.color':'w', 'axes.labelcolor':'w'})
seed=2811
np.random.seed(seed)
tf.random.set_seed(seed)
pip install kaggle --upgrade
os.environ['KAGGLE_USERNAME'] = "******"
os.environ['KAGGLE_KEY'] = "5912caabf0d1fa350842f382da374953"
#https://www.kaggle.com/rounakbanik/the-movies-dataset
!kaggle datasets download rounakbanik/the-movies-dataset
!unzip -o 'the-movies-dataset.zip'
#code used to plot a graph
from matplotlib import pylab as plt
get_ipython().magic('matplotlib inline')
# tweak figure appearance
rc = {'xtick.labelsize': 16,
'ytick.labelsize': 16,
'axes.labelsize': 18,
'axes.labelweight': '900',
'legend.fontsize': 20,
'font.family': 'cursive',
'font.monospace': 'Nimbus Mono L',
'lines.linewidth': 2,
'lines.markersize': 9,
'xtick.major.pad': 20}
plt.rc_context(rc=rc)
plt.rcParams['font.family'] = 'serif'
plt.rcParams['axes.labelsize'] = 22
plt.rcParams['figure.figsize'] = 9, 6 # make figures larger in notebook
def plot_results(results, title, xlabels, ylabel="Success Rate"):
'''Plot a bar graph of results'''
ind = np.arange(len(results))
width = 0.4
plt.bar(ind, results, width, color="#1AADA4")
plt.ylabel(ylabel)
plt.ylim(ymax=100)
plt.xticks(ind+width/2.0, xlabels)
plt.title(title)