Python matplotlib.pylab 模块，grid() 实例源码
我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用matplotlib.pylab.grid()。
def plot(traj, x, y, **kwargs):
""" Create a matplotlib plot of property x against property y
Args:
x,y (str): names of the properties
**kwargs (dict): kwargs for :meth:`matplotlib.pylab.plot`
Returns:
List[matplotlib.lines.Lines2D]: the lines that were plotted
"""
from matplotlib import pylab
xl = yl = None
if type(x) is str:
strx = x
x = getattr(traj, x)
xl = '%s / %s' % (strx, getattr(x, 'units', 'dimensionless'))
if type(y) is str:
stry = y
y = getattr(traj, y)
yl = '%s / %s' % (stry, getattr(y, 'units', 'dimensionless'))
plt = pylab.plot(x, y, **kwargs)
pylab.xlabel(xl); pylab.ylabel(yl); pylab.grid()
return plt
def plot_confusion_matrix(cm, label_list, title='Confusion matrix', cmap=None):
from matplotlib import pylab
cm = np.asarray(cm, dtype=np.float32)
for i, row in enumerate(cm):
cm[i] = cm[i] / np.sum(cm[i])
#import matplotlib.pyplot as plt
#plt.ion()
pylab.clf()
pylab.matshow(cm, fignum=False, cmap='Blues', vmin=0, vmax=1.0)
ax = pylab.axes()
ax.set_xticks(range(len(label_list)))
ax.set_xticklabels(label_list, rotation='vertical')
ax.xaxis.set_ticks_position('bottom')
ax.set_yticks(range(len(label_list)))
ax.set_yticklabels(label_list)
pylab.title(title)
pylab.colorbar()
pylab.grid(False)
pylab.xlabel('Predicted class')
pylab.ylabel('True class')
pylab.grid(False)
pylab.savefig('test.jpg')
pylab.show()
def plot_entropy():
pylab.clf()
pylab.figure(num=None, figsize=(5, 4))
title = "Entropy $H(X)$"
pylab.title(title)
pylab.xlabel("$P(X=$coin will show heads up$)$")
pylab.ylabel("$H(X)$")
pylab.xlim(xmin=0, xmax=1.1)
x = np.arange(0.001, 1, 0.001)
y = -x * np.log2(x) - (1 - x) * np.log2(1 - x)
pylab.plot(x, y)
# pylab.xticks([w*7*24 for w in [0,1,2,3,4]], ['week %i'%(w+1) for w in
# [0,1,2,3,4]])
pylab.autoscale(tight=True)
pylab.grid(True)
filename = "entropy_demo.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_clustering(x, y, title, mx=None, ymax=None, xmin=None, km=None):
pylab.figure(num=None, figsize=(8, 6))
if km:
pylab.scatter(x, y, s=50, c=km.predict(list(zip(x, y))))
else:
pylab.scatter(x, y, s=50)
pylab.title(title)
pylab.xlabel("Occurrence word 1")
pylab.ylabel("Occurrence word 2")
pylab.autoscale(tight=True)
pylab.ylim(ymin=0, ymax=1)
pylab.xlim(xmin=0, xmax=1)
pylab.grid(True, linestyle='-', color='0.75')
return pylab
def plot_confusion_matrix(cm, genre_list, name, title):
pylab.clf()
pylab.matshow(cm, fignum=False, cmap='Blues', vmin=0, vmax=1.0)
ax = pylab.axes()
ax.set_xticks(range(len(genre_list)))
ax.set_xticklabels(genre_list)
ax.xaxis.set_ticks_position("bottom")
ax.set_yticks(range(len(genre_list)))
ax.set_yticklabels(genre_list)
pylab.title(title)
pylab.colorbar()
pylab.grid(False)
pylab.show()
pylab.xlabel('Predicted class')
pylab.ylabel('True class')
pylab.grid(False)
pylab.savefig(
os.path.join(CHART_DIR, "confusion_matrix_%s.png" % name), bbox_inches="tight")
def plot_roc(auc_score, name, tpr, fpr, label=None):
pylab.clf()
pylab.figure(num=None, figsize=(5, 4))
pylab.grid(True)
pylab.plot([0, 1], [0, 1], 'k--')
pylab.plot(fpr, tpr)
pylab.fill_between(fpr, tpr, alpha=0.5)
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('False Positive Rate')
pylab.ylabel('True Positive Rate')
pylab.title('ROC curve (AUC = %0.2f) / %s' %
(auc_score, label), verticalalignment="bottom")
pylab.legend(loc="lower right")
filename = name.replace(" ", "_")
pylab.savefig(
os.path.join(CHART_DIR, "roc_" + filename + ".png"), bbox_inches="tight")
def plotKChart(self, misClassDict, saveFigPath):
kList = []
misRateList = []
for k, misClassNum in misClassDict.iteritems():
kList.append(k)
misRateList.append(1.0 - 1.0/k*misClassNum)
fig = plt.figure(saveFigPath)
plt.plot(kList, misRateList, 'r--')
plt.title(saveFigPath)
plt.xlabel('k Num.')
plt.ylabel('Misclassified Rate')
plt.legend(saveFigPath)
plt.grid(True)
plt.savefig(saveFigPath)
plt.show()
################################### PART3 TEST ########################################
# ??
def plot_penalty_vl(debug, tag, fold_exp):
plt.close("all")
vl = np.array(debug["penalty"])
fig = plt.figure(figsize=(15, 10.8), dpi=300)
names = debug["names"]
for i in range(vl.shape[1]):
if vl.shape[1] > 1:
plt.plot(vl[:, i], label="layer_"+str(names[i]))
else:
plt.plot(vl[:], label="layer_"+str(names[i]))
plt.xlabel("mini-batchs")
plt.ylabel("value of penlaty")
plt.title(
"Penalty value over layers:" + "_".join([str(k) for k in names]) +
". tag:" + tag)
plt.legend(loc='upper right', fancybox=True, shadow=True, prop={'size': 8})
plt.grid(True)
fig.savefig(fold_exp+"/penalty.png", bbox_inches='tight')
plt.close('all')
del fig
def plot_confusion_matrix(cm, plot_title, filename, genres=None):
if not genres:
genres = GENRES
pylab.clf()
pylab.matshow(cm, fignum=False, cmap='Blues', vmin=0, vmax=100.0)
axes = pylab.axes()
axes.set_xticks(range(len(genres)))
axes.set_xticklabels(genres, rotation=45)
axes.set_yticks(range(len(genres)))
axes.set_yticklabels(genres)
axes.xaxis.set_ticks_position("bottom")
pylab.title(plot_title, fontsize=14)
pylab.colorbar()
pylab.xlabel('Predicted class', fontsize=12)
pylab.ylabel('Correct class', fontsize=12)
pylab.grid(False)
#pylab.show()
pylab.savefig(os.path.join(PLOTS_DIR, "cm_%s.eps" % filename), bbox_inches="tight")
def plot_confusion_matrix(cm, label_list, title='Confusion matrix', cmap=None):
from matplotlib import pylab
cm = np.asarray(cm, dtype=np.float32)
for i, row in enumerate(cm):
cm[i] = cm[i] / np.sum(cm[i])
#import matplotlib.pyplot as plt
#plt.ion()
pylab.clf()
pylab.matshow(cm, fignum=False, cmap='Blues', vmin=0, vmax=1.0)
ax = pylab.axes()
ax.set_xticks(range(len(label_list)))
ax.set_xticklabels(label_list, rotation='vertical')
ax.xaxis.set_ticks_position('bottom')
ax.set_yticks(range(len(label_list)))
ax.set_yticklabels(label_list)
pylab.title(title)
pylab.colorbar()
pylab.grid(False)
pylab.xlabel('Predicted class')
pylab.ylabel('True class')
pylab.grid(False)
pylab.savefig('test.jpg')
pylab.show()
def plot_forest_all_proba(y_proba_all, y_gt):
from matplotlib import pylab
N = len(y_gt)
num_tree = len(y_proba_all)
pylab.clf()
mat = np.zeros((num_tree, N))
LOGGER.info('mat.shape={}'.format(mat.shape))
for i in range(num_tree):
mat[i,:] = y_proba_all[i][(range(N), y_gt)]
pylab.matshow(mat, fignum=False, cmap='Blues', vmin=0, vmax=1.0)
pylab.grid(False)
pylab.show()
def imageSegy(Data):
"""
imageSegy(Data)
Image segy Data
"""
import matplotlib.pylab as plt
plt.imshow(Data)
plt.title('pymat test')
plt.grid(True)
plt.show()
#%%
def wiggle(Data,SH,skipt=1,maxval=8,lwidth=.1):
"""
wiggle(Data,SH)
"""
import matplotlib.pylab as plt
t = range(SH['ns'])
# t = range(SH['ns'])*SH['dt']/1000000;
for i in range(0,SH['ntraces'],skipt):
# trace=zeros(SH['ns']+2)
# dtrace=Data[:,i]
# trace[1:SH['ns']]=Data[:,i]
# trace[SH['ns']+1]=0
trace=Data[:,i]
trace[0]=0
trace[SH['ns']-1]=0
plt.plot(i+trace/maxval,t,color='black',linewidth=lwidth)
for a in range(len(trace)):
if (trace[a]<0):
trace[a]=0;
# pylab.fill(i+Data[:,i]/maxval,t,color='k',facecolor='g')
plt.fill(i+Data[:,i]/maxval,t,'k',linewidth=0)
plt.title(SH['filename'])
plt.grid(True)
plt.show()
#%%
def plot_pr(auc_score, name, phase, precision, recall, label=None):
pylab.clf()
pylab.figure(num=None, figsize=(5, 4))
pylab.grid(True)
pylab.fill_between(recall, precision, alpha=0.5)
pylab.plot(recall, precision, lw=1)
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('Recall')
pylab.ylabel('Precision')
pylab.title('P/R curve (AUC=%0.2f) / %s' % (auc_score, label))
filename = name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, "pr_%s_%s.png" %
(filename, phase)), bbox_inches="tight")
def plot_log():
pylab.clf()
pylab.figure(num=None, figsize=(6, 5))
x = np.arange(0.001, 1, 0.001)
y = np.log(x)
pylab.title('Relationship between probabilities and their logarithm')
pylab.plot(x, y)
pylab.grid(True)
pylab.xlabel('P')
pylab.ylabel('log(P)')
filename = 'log_probs.png'
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_feat_hist(data_name_list, filename=None):
pylab.clf()
num_rows = 1 + (len(data_name_list) - 1) / 2
num_cols = 1 if len(data_name_list) == 1 else 2
pylab.figure(figsize=(5 * num_cols, 4 * num_rows))
for i in range(num_rows):
for j in range(num_cols):
pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
x, name = data_name_list[i * num_cols + j]
pylab.title(name)
pylab.xlabel('Value')
pylab.ylabel('Density')
# the histogram of the data
max_val = np.max(x)
if max_val <= 1.0:
bins = 50
elif max_val > 50:
bins = 50
else:
bins = max_val
n, bins, patches = pylab.hist(
x, bins=bins, normed=1, facecolor='green', alpha=0.75)
pylab.grid(True)
if not filename:
filename = "feat_hist_%s.png" % name
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_bias_variance(data_sizes, train_errors, test_errors, name):
pylab.clf()
pylab.ylim([0.0, 1.0])
pylab.xlabel('Data set size')
pylab.ylabel('Error')
pylab.title("Bias-Variance for '%s'" % name)
pylab.plot(
data_sizes, train_errors, "-", data_sizes, test_errors, "--", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid()
pylab.savefig(os.path.join(CHART_DIR, "bv_" + name + ".png"))
def plot_pr(auc_score, name, precision, recall, label=None):
pylab.figure(num=None, figsize=(6, 5))
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('Recall')
pylab.ylabel('Precision')
pylab.title('P/R (AUC=%0.2f) / %s' % (auc_score, label))
pylab.fill_between(recall, precision, alpha=0.5)
pylab.grid(True, linestyle='-', color='0.75')
pylab.plot(recall, precision, lw=1)
filename = name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, "pr_" + filename + ".png"))
def plot_feat_hist(data_name_list, filename=None):
if len(data_name_list) > 1:
assert filename is not None
pylab.figure(num=None, figsize=(8, 6))
num_rows = int(1 + (len(data_name_list) - 1) / 2)
num_cols = int(1 if len(data_name_list) == 1 else 2)
pylab.figure(figsize=(5 * num_cols, 4 * num_rows))
for i in range(num_rows):
for j in range(num_cols):
pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
x, name = data_name_list[i * num_cols + j]
pylab.title(name)
pylab.xlabel('Value')
pylab.ylabel('Fraction')
# the histogram of the data
max_val = np.max(x)
if max_val <= 1.0:
bins = 50
elif max_val > 50:
bins = 50
else:
bins = max_val
n, bins, patches = pylab.hist(
x, bins=bins, normed=1, alpha=0.75)
pylab.grid(True)
if not filename:
filename = "feat_hist_%s.png" % name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_bias_variance(data_sizes, train_errors, test_errors, name, title):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('Data set size')
pylab.ylabel('Error')
pylab.title("Bias-Variance for '%s'" % name)
pylab.plot(
data_sizes, test_errors, "--", data_sizes, train_errors, "b-", lw=1)
pylab.legend(["test error", "train error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(
os.path.join(CHART_DIR, "bv_" + name.replace(" ", "_") + ".png"), bbox_inches="tight")
def plot_k_complexity(ks, train_errors, test_errors):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('k')
pylab.ylabel('Error')
pylab.title('Errors for for different values of $k$')
pylab.plot(
ks, test_errors, "--", ks, train_errors, "-", lw=1)
pylab.legend(["test error", "train error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(
os.path.join(CHART_DIR, "kcomplexity.png"), bbox_inches="tight")
def plot_log():
pylab.clf()
x = np.arange(0.001, 1, 0.001)
y = np.log(x)
pylab.title('Relationship between probabilities and their logarithm')
pylab.plot(x, y)
pylab.grid(True)
pylab.xlabel('P')
pylab.ylabel('log(P)')
filename = 'log_probs.png'
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_feat_hist(data_name_list, filename=None):
pylab.clf()
num_rows = 1 + (len(data_name_list) - 1) / 2
num_cols = 1 if len(data_name_list) == 1 else 2
pylab.figure(figsize=(5 * num_cols, 4 * num_rows))
for i in range(num_rows):
for j in range(num_cols):
pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
x, name = data_name_list[i * num_cols + j]
pylab.title(name)
pylab.xlabel('Value')
pylab.ylabel('Density')
# the histogram of the data
max_val = np.max(x)
if max_val <= 1.0:
bins = 50
elif max_val > 50:
bins = 50
else:
bins = max_val
n, bins, patches = pylab.hist(
x, bins=bins, normed=1, facecolor='green', alpha=0.75)
pylab.grid(True)
if not filename:
filename = "feat_hist_%s.png" % name
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_bias_variance(data_sizes, train_errors, test_errors, name):
pylab.clf()
pylab.ylim([0.0, 1.0])
pylab.xlabel('Data set size')
pylab.ylabel('Error')
pylab.title("Bias-Variance for '%s'" % name)
pylab.plot(
data_sizes, train_errors, "-", data_sizes, test_errors, "--", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid(True)
pylab.savefig(os.path.join(CHART_DIR, "bv_" + name + ".png"))
def plot_debug_grad(debug, tag, fold_exp, trg):
plt.close("all")
# f = plt.figure(figsize=(15, 10.8), dpi=300)
nbr_rows = int(len(debug["grad_sup"][0])/2)
f, axs = plt.subplots(nbr_rows, 2, sharex=True, sharey=False,
figsize=(15, 12.8), dpi=300)
if trg == "sup":
grad = np.array(debug["grad_sup"])
elif trg == "hint":
grad = np.array(debug["grad_hint"])
print grad.shape, trg
j = 0
for i in range(0, nbr_rows*2, 2):
w_vl = grad[:, i]
b_vl = grad[:, i+1]
axs[j, 0].plot(w_vl, label=trg)
axs[j, 0].set_title("w"+str(j))
axs[j, 1].plot(b_vl, label=trg)
axs[j, 1].set_title("b"+str(j))
axs[j, 0].grid(True)
axs[j, 1].grid(True)
j += 1
f.suptitle("Grad sup/hint:" + tag, fontsize=8)
plt.legend()
f.savefig(fold_exp+"/grad_" + trg + ".png", bbox_inches='tight')
plt.close("all")
del f
def plot_debug_ratio_grad(debug, fold_exp, r="h/s"):
plt.close("all")
# f = plt.figure(figsize=(15, 10.8), dpi=300)
nbr_rows = int(len(debug["grad_sup"][0])/2)
f, axs = plt.subplots(nbr_rows, 2, sharex=True, sharey=False,
figsize=(15, 12.8), dpi=300)
grads = np.array(debug["grad_sup"])
gradh = np.array(debug["grad_hint"])
if gradh.size != grads.size:
print "Can't calculate the ratio. It looks like you divided the " +\
"hint batch..."
return 0
print gradh.shape, grads.shape
j = 0
for i in range(0, nbr_rows*2, 2):
w_vls = grads[:, i]
b_vls = grads[:, i+1]
w_vl_h = gradh[:, i]
b_vlh = gradh[:, i+1]
if r == "h/s":
ratio_w = np.divide(w_vl_h, w_vls)
ratio_b = np.divide(b_vlh, b_vls)
elif r == "s/h":
ratio_w = np.divide(w_vls, w_vl_h)
ratio_b = np.divide(b_vls, b_vlh)
else:
raise ValueError("Either h/s or s/h.")
axs[j, 0].plot(ratio_w, label=r)
axs[j, 0].set_title("w"+str(j))
axs[j, 1].plot(ratio_b, label=r)
axs[j, 1].set_title("b"+str(j))
axs[j, 0].grid(True)
axs[j, 1].grid(True)
j += 1
f.suptitle("Ratio gradient: " + r, fontsize=8)
plt.legend()
f.savefig(fold_exp+"/ratio_grad_" + r.replace("/", "-") + ".png",
bbox_inches='tight')
plt.close("all")
del f
def plot_forest_all_proba(y_proba_all, y_gt):
from matplotlib import pylab
N = len(y_gt)
num_tree = len(y_proba_all)
pylab.clf()
mat = np.zeros((num_tree, N))
LOGGER.info('mat.shape={}'.format(mat.shape))
for i in range(num_tree):
mat[i,:] = y_proba_all[i][(range(N), y_gt)]
pylab.matshow(mat, fignum=False, cmap='Blues', vmin=0, vmax=1.0)
pylab.grid(False)
pylab.show()
def plot_roc(auc_score, name, fpr, tpr):
pylab.figure(num=None, figsize=(6, 5))
pylab.plot([0, 1], [0, 1], 'k--')
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('False Positive Rate')
pylab.ylabel('True Positive Rate')
pylab.title('Receiver operating characteristic (AUC=%0.2f)\n%s' % (
auc_score, name))
pylab.legend(loc="lower right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.fill_between(tpr, fpr, alpha=0.5)
pylab.plot(fpr, tpr, lw=1)
pylab.savefig(os.path.join(CHART_DIR, "roc_" + name.replace(" ", "_")+ ".png"))
def plot_pr(auc_score, name, precision, recall, label=None):
pylab.figure(num=None, figsize=(6, 5))
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('Recall')
pylab.ylabel('Precision')
pylab.title('P/R (AUC=%0.2f) / %s' % (auc_score, label))
pylab.fill_between(recall, precision, alpha=0.5)
pylab.grid(True, linestyle='-', color='0.75')
pylab.plot(recall, precision, lw=1)
filename = name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, "pr_" + filename + ".png"))
def plot_feat_hist(data_name_list, filename=None):
if len(data_name_list)>1:
assert filename is not None
pylab.figure(num=None, figsize=(8, 6))
num_rows = 1 + (len(data_name_list) - 1) / 2
num_cols = 1 if len(data_name_list) == 1 else 2
pylab.figure(figsize=(5 * num_cols, 4 * num_rows))
for i in range(num_rows):
for j in range(num_cols):
pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
x, name = data_name_list[i * num_cols + j]
pylab.title(name)
pylab.xlabel('Value')
pylab.ylabel('Fraction')
# the histogram of the data
max_val = np.max(x)
if max_val <= 1.0:
bins = 50
elif max_val > 50:
bins = 50
else:
bins = max_val
n, bins, patches = pylab.hist(
x, normed=1, facecolor='blue', alpha=0.75)
pylab.grid(True)
if not filename:
filename = "feat_hist_%s.png" % name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_bias_variance(data_sizes, train_errors, test_errors, name, title):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('Data set size')
pylab.ylabel('Error')
pylab.title("Bias-Variance for '%s'" % name)
pylab.plot(
data_sizes, test_errors, "--", data_sizes, train_errors, "b-", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(os.path.join(CHART_DIR, "bv_" + name.replace(" ", "_") + ".png"), bbox_inches="tight")
def plot_k_complexity(ks, train_errors, test_errors):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('k')
pylab.ylabel('Error')
pylab.title('Errors for for different values of k')
pylab.plot(
ks, test_errors, "--", ks, train_errors, "-", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(os.path.join(CHART_DIR, "kcomplexity.png"), bbox_inches="tight")
def plot_pr(auc_score, name, precision, recall, label=None):
pylab.figure(num=None, figsize=(6, 5))
pylab.xlim([0.0, 1.0])
pylab.ylim([0.0, 1.0])
pylab.xlabel('Recall')
pylab.ylabel('Precision')
pylab.title('P/R (AUC=%0.2f) / %s' % (auc_score, label))
pylab.fill_between(recall, precision, alpha=0.5)
pylab.grid(True, linestyle='-', color='0.75')
pylab.plot(recall, precision, lw=1)
filename = name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, "pr_" + filename + ".png"))
def plot_feat_hist(data_name_list, filename=None):
if len(data_name_list)>1:
assert filename is not None
pylab.figure(num=None, figsize=(8, 6))
num_rows = 1 + (len(data_name_list) - 1) / 2
num_cols = 1 if len(data_name_list) == 1 else 2
pylab.figure(figsize=(5 * num_cols, 4 * num_rows))
for i in range(num_rows):
for j in range(num_cols):
pylab.subplot(num_rows, num_cols, 1 + i * num_cols + j)
x, name = data_name_list[i * num_cols + j]
pylab.title(name)
pylab.xlabel('Value')
pylab.ylabel('Fraction')
# the histogram of the data
max_val = np.max(x)
if max_val <= 1.0:
bins = 50
elif max_val > 50:
bins = 50
else:
bins = max_val
n, bins, patches = pylab.hist(
x, normed=1, facecolor='blue', alpha=0.75)
pylab.grid(True)
if not filename:
filename = "feat_hist_%s.png" % name.replace(" ", "_")
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_bias_variance(data_sizes, train_errors, test_errors, name, title):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('Data set size')
pylab.ylabel('Error')
pylab.title("Bias-Variance for '%s'" % name)
pylab.plot(
data_sizes, test_errors, "--", data_sizes, train_errors, "b-", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(os.path.join(CHART_DIR, "bv_" + name.replace(" ", "_") + ".png"), bbox_inches="tight")
def plot_k_complexity(ks, train_errors, test_errors):
pylab.figure(num=None, figsize=(6, 5))
pylab.ylim([0.0, 1.0])
pylab.xlabel('k')
pylab.ylabel('Error')
pylab.title('Errors for for different values of k')
pylab.plot(
ks, test_errors, "--", ks, train_errors, "-", lw=1)
pylab.legend(["train error", "test error"], loc="upper right")
pylab.grid(True, linestyle='-', color='0.75')
pylab.savefig(os.path.join(CHART_DIR, "kcomplexity.png"), bbox_inches="tight")
def plot_fig(values, title, x_str, y_str, path, best_iter, std_vals=None):
"""Plot some values.
Input:
values: list or numpy.ndarray of values to plot (y)
title: string; the title of the plot.
x_str: string; the name of the x axis.
y_str: string; the name of the y axis.
path: string; path where to save the figure.
best_iter: integer. The epoch of the best iteration.
std_val: List or numpy.ndarray of standad deviation values that
corresponds to each value in 'values'.
"""
floating = 6
prec = "%." + str(floating) + "f"
if best_iter >= 0:
if isinstance(values, list):
if best_iter >= len(values):
best_iter = -1
if isinstance(values, np.ndarray):
if best_iter >= np.size:
best_iter = -1
v = str(prec % np.float(values[best_iter]))
else:
v = str(prec % np.float(values[-1]))
best_iter = -1
if best_iter == -1:
best_iter = len(values)
fig = plt.figure()
plt.plot(
values,
label="lower val: " + v + " at " + str(best_iter) + " " +
x_str)
plt.xlabel(x_str)
plt.ylabel(y_str)
plt.title(title, fontsize=8)
plt.legend(loc='upper right', fancybox=True, shadow=True, prop={'size': 8})
plt.grid(True)
fig.savefig(path, bbox_inches='tight')
plt.close('all')
del fig
def plot(self, *args, **kwargs):
"""
Plot samples from the frequency distribution
displaying the most frequent sample first. If an integer
parameter is supplied, stop after this many samples have been
plotted. For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param title: The title for the graph
:type title: str
:param cumulative: A flag to specify whether the plot is cumulative (default = False)
:type title: bool
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
if len(args) == 0:
args = [len(self)]
samples = [item for item, _ in self.most_common(*args)]
cumulative = _get_kwarg(kwargs, 'cumulative', False)
if cumulative:
freqs = list(self._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
else:
freqs = [self[sample] for sample in samples]
ylabel = "Counts"
# percents = [f * 100 for f in freqs] only in ProbDist?
pylab.grid(True, color="silver")
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
if "title" in kwargs:
pylab.title(kwargs["title"])
del kwargs["title"]
pylab.plot(freqs, **kwargs)
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot(self, *args, **kwargs):
"""
Plot the given samples from the conditional frequency distribution.
For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param samples: The samples to plot
:type samples: list
:param title: The title for the graph
:type title: str
:param conditions: The conditions to plot (default is all)
:type conditions: list
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
cumulative = _get_kwarg(kwargs, 'cumulative', False)
conditions = _get_kwarg(kwargs, 'conditions', sorted(self.conditions()))
title = _get_kwarg(kwargs, 'title', '')
samples = _get_kwarg(kwargs, 'samples',
sorted(set(v for c in conditions for v in self[c]))) # this computation could be wasted
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
for condition in conditions:
if cumulative:
freqs = list(self[condition]._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
legend_loc = 'lower right'
else:
freqs = [self[condition][sample] for sample in samples]
ylabel = "Counts"
legend_loc = 'upper right'
# percents = [f * 100 for f in freqs] only in ConditionalProbDist?
kwargs['label'] = "%s" % condition
pylab.plot(freqs, *args, **kwargs)
pylab.legend(loc=legend_loc)
pylab.grid(True, color="silver")
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
if title:
pylab.title(title)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot_mi_demo():
np.random.seed(0) # to reproduce the data later on
pylab.clf()
pylab.figure(num=None, figsize=(8, 8))
x = np.arange(0, 10, 0.2)
pylab.subplot(221)
y = 0.5 * x + norm.rvs(1, scale=.01, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(222)
y = 0.5 * x + norm.rvs(1, scale=.1, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(223)
y = 0.5 * x + norm.rvs(1, scale=1, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(224)
y = norm.rvs(1, scale=10, size=len(x))
_plot_mi_func(x, y)
pylab.autoscale(tight=True)
pylab.grid(True)
filename = "mi_demo_1.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
pylab.clf()
pylab.figure(num=None, figsize=(8, 8))
x = np.arange(-5, 5, 0.2)
pylab.subplot(221)
y = 0.5 * x ** 2 + norm.rvs(1, scale=.01, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(222)
y = 0.5 * x ** 2 + norm.rvs(1, scale=.1, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(223)
y = 0.5 * x ** 2 + norm.rvs(1, scale=1, size=len(x))
_plot_mi_func(x, y)
pylab.subplot(224)
y = 0.5 * x ** 2 + norm.rvs(1, scale=10, size=len(x))
_plot_mi_func(x, y)
pylab.autoscale(tight=True)
pylab.grid(True)
filename = "mi_demo_2.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_correlation_demo():
np.random.seed(0) # to reproduce the data later on
pylab.clf()
pylab.figure(num=None, figsize=(8, 8))
x = np.arange(0, 10, 0.2)
pylab.subplot(221)
y = 0.5 * x + norm.rvs(1, scale=.01, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(222)
y = 0.5 * x + norm.rvs(1, scale=.1, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(223)
y = 0.5 * x + norm.rvs(1, scale=1, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(224)
y = norm.rvs(1, scale=10, size=len(x))
_plot_correlation_func(x, y)
pylab.autoscale(tight=True)
pylab.grid(True)
filename = "corr_demo_1.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
pylab.clf()
pylab.figure(num=None, figsize=(8, 8))
x = np.arange(-5, 5, 0.2)
pylab.subplot(221)
y = 0.5 * x ** 2 + norm.rvs(1, scale=.01, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(222)
y = 0.5 * x ** 2 + norm.rvs(1, scale=.1, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(223)
y = 0.5 * x ** 2 + norm.rvs(1, scale=1, size=len(x))
_plot_correlation_func(x, y)
pylab.subplot(224)
y = 0.5 * x ** 2 + norm.rvs(1, scale=10, size=len(x))
_plot_correlation_func(x, y)
pylab.autoscale(tight=True)
pylab.grid(True)
filename = "corr_demo_2.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_simple_demo_1():
pylab.clf()
fig = pylab.figure(num=None, figsize=(10, 4))
pylab.subplot(121)
title = "Original feature space"
pylab.title(title)
pylab.xlabel("$X_1$")
pylab.ylabel("$X_2$")
x1 = np.arange(0, 10, .2)
x2 = x1 + np.random.normal(scale=1, size=len(x1))
good = (x1 > 5) | (x2 > 5)
bad = ~good
x1g = x1[good]
x2g = x2[good]
pylab.scatter(x1g, x2g, edgecolor="blue", facecolor="blue")
x1b = x1[bad]
x2b = x2[bad]
pylab.scatter(x1b, x2b, edgecolor="red", facecolor="white")
pylab.grid(True)
pylab.subplot(122)
X = np.c_[(x1, x2)]
pca = decomposition.PCA(n_components=1)
Xtrans = pca.fit_transform(X)
Xg = Xtrans[good]
Xb = Xtrans[bad]
pylab.scatter(
Xg[:, 0], np.zeros(len(Xg)), edgecolor="blue", facecolor="blue")
pylab.scatter(
Xb[:, 0], np.zeros(len(Xb)), edgecolor="red", facecolor="white")
title = "Transformed feature space"
pylab.title(title)
pylab.xlabel("$X'$")
fig.axes[1].get_yaxis().set_visible(False)
print(pca.explained_variance_ratio_)
pylab.grid(True)
pylab.autoscale(tight=True)
filename = "pca_demo_1.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plot_simple_demo_2():
pylab.clf()
fig = pylab.figure(num=None, figsize=(10, 4))
pylab.subplot(121)
title = "Original feature space"
pylab.title(title)
pylab.xlabel("$X_1$")
pylab.ylabel("$X_2$")
x1 = np.arange(0, 10, .2)
x2 = x1 + np.random.normal(scale=1, size=len(x1))
good = x1 > x2
bad = ~good
x1g = x1[good]
x2g = x2[good]
pylab.scatter(x1g, x2g, edgecolor="blue", facecolor="blue")
x1b = x1[bad]
x2b = x2[bad]
pylab.scatter(x1b, x2b, edgecolor="red", facecolor="white")
pylab.grid(True)
pylab.subplot(122)
X = np.c_[(x1, x2)]
pca = decomposition.PCA(n_components=1)
Xtrans = pca.fit_transform(X)
Xg = Xtrans[good]
Xb = Xtrans[bad]
pylab.scatter(
Xg[:, 0], np.zeros(len(Xg)), edgecolor="blue", facecolor="blue")
pylab.scatter(
Xb[:, 0], np.zeros(len(Xb)), edgecolor="red", facecolor="white")
title = "Transformed feature space"
pylab.title(title)
pylab.xlabel("$X'$")
fig.axes[1].get_yaxis().set_visible(False)
print(pca.explained_variance_ratio_)
pylab.grid(True)
pylab.autoscale(tight=True)
filename = "pca_demo_2.png"
pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")
def plotScatter(self, xList, yList, saveFigPath):
'''
?????? xList ???? yList ????????????
?????? saveFigPath ????
:param xList: ????
:param yList: ????
:param saveFigPath: ????????
:return:
'''
# ????????????
# ??????????? 2
# ???????? 2 ?????
if len(xList[0]) >= 2:
x1List = map(lambda x: x[0], xList)
x2List = map(lambda x: x[1], xList)
else:
# 1 ? 2 ???????? 2 ?
x1List = x2List = map(lambda x: x[0], xList)
# ????
scatterFig= plt.figure(saveFigPath)
# ?????????
colorDict = {-1: 'm', 1: 'r', 2: 'b', 3: 'pink', 4: 'orange'}
# ?????
map(lambda idx: \
plt.scatter(x1List[idx], \
x2List[idx], \
marker='o', \
color=colorDict[yList[idx]], \
label=yList[idx]), \
xrange(len(x1List)))
# ?????????
# ySet = set(yList)
# map(lambda y: \
# plt.legend(str(y), \
# loc='best'), \
# ySet)
# ??????????????
plt.title(saveFigPath)
plt.xlabel(r'$x^1$')
plt.ylabel(r'$x^2$')
plt.grid(True)
plt.savefig(saveFigPath)
plt.show()
def plot(self, *args, **kwargs):
"""
Plot samples from the frequency distribution
displaying the most frequent sample first. If an integer
parameter is supplied, stop after this many samples have been
plotted. For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param title: The title for the graph
:type title: str
:param cumulative: A flag to specify whether the plot is cumulative (default = False)
:type title: bool
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
if len(args) == 0:
args = [len(self)]
samples = [item for item, _ in self.most_common(*args)]
cumulative = _get_kwarg(kwargs, 'cumulative', False)
if cumulative:
freqs = list(self._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
else:
freqs = [self[sample] for sample in samples]
ylabel = "Counts"
# percents = [f * 100 for f in freqs] only in ProbDist?
pylab.grid(True, color="silver")
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
if "title" in kwargs:
pylab.title(kwargs["title"])
del kwargs["title"]
pylab.plot(freqs, **kwargs)
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot(self, *args, **kwargs):
"""
Plot the given samples from the conditional frequency distribution.
For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param samples: The samples to plot
:type samples: list
:param title: The title for the graph
:type title: str
:param conditions: The conditions to plot (default is all)
:type conditions: list
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
cumulative = _get_kwarg(kwargs, 'cumulative', False)
conditions = _get_kwarg(kwargs, 'conditions', sorted(self.conditions()))
title = _get_kwarg(kwargs, 'title', '')
samples = _get_kwarg(kwargs, 'samples',
sorted(set(v for c in conditions for v in self[c]))) # this computation could be wasted
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
for condition in conditions:
if cumulative:
freqs = list(self[condition]._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
legend_loc = 'lower right'
else:
freqs = [self[condition][sample] for sample in samples]
ylabel = "Counts"
legend_loc = 'upper right'
# percents = [f * 100 for f in freqs] only in ConditionalProbDist?
kwargs['label'] = "%s" % condition
pylab.plot(freqs, *args, **kwargs)
pylab.legend(loc=legend_loc)
pylab.grid(True, color="silver")
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
if title:
pylab.title(title)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot(self, *args, **kwargs):
"""
Plot samples from the frequency distribution
displaying the most frequent sample first. If an integer
parameter is supplied, stop after this many samples have been
plotted. For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param title: The title for the graph
:type title: str
:param cumulative: A flag to specify whether the plot is cumulative (default = False)
:type title: bool
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
if len(args) == 0:
args = [len(self)]
samples = [item for item, _ in self.most_common(*args)]
cumulative = _get_kwarg(kwargs, 'cumulative', False)
if cumulative:
freqs = list(self._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
else:
freqs = [self[sample] for sample in samples]
ylabel = "Counts"
# percents = [f * 100 for f in freqs] only in ProbDist?
pylab.grid(True, color="silver")
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
if "title" in kwargs:
pylab.title(kwargs["title"])
del kwargs["title"]
pylab.plot(freqs, **kwargs)
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot(self, *args, **kwargs):
"""
Plot the given samples from the conditional frequency distribution.
For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param samples: The samples to plot
:type samples: list
:param title: The title for the graph
:type title: str
:param conditions: The conditions to plot (default is all)
:type conditions: list
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
cumulative = _get_kwarg(kwargs, 'cumulative', False)
conditions = _get_kwarg(kwargs, 'conditions', sorted(self.conditions()))
title = _get_kwarg(kwargs, 'title', '')
samples = _get_kwarg(kwargs, 'samples',
sorted(set(v for c in conditions for v in self[c]))) # this computation could be wasted
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
for condition in conditions:
if cumulative:
freqs = list(self[condition]._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
legend_loc = 'lower right'
else:
freqs = [self[condition][sample] for sample in samples]
ylabel = "Counts"
legend_loc = 'upper right'
# percents = [f * 100 for f in freqs] only in ConditionalProbDist?
kwargs['label'] = "%s" % condition
pylab.plot(freqs, *args, **kwargs)
pylab.legend(loc=legend_loc)
pylab.grid(True, color="silver")
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
if title:
pylab.title(title)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()
def plot_fig(values, title, x_str, y_str, path, best_iter, std_vals=None):
"""Plot some values.
Input:
values: list or numpy.ndarray of values to plot (y)
title: string; the title of the plot.
x_str: string; the name of the x axis.
y_str: string; the name of the y axis.
path: string; path where to save the figure.
best_iter: integer. The epoch of the best iteration.
std_val: List or numpy.ndarray of standad deviation values that
corresponds to each value in 'values'.
"""
floating = 6
prec = "%." + str(floating) + "f"
if best_iter >= 0:
if isinstance(values, list):
if best_iter >= len(values):
best_iter = -1
if isinstance(values, np.ndarray):
if best_iter >= np.size:
best_iter = -1
v = str(prec % np.float(values[best_iter]))
else:
v = str(prec % np.float(values[-1]))
best_iter = -1
if best_iter == -1:
best_iter = len(values)
fig = plt.figure()
plt.plot(
values,
label="lower val: " + v + " at " + str(best_iter) + " " +
x_str)
plt.xlabel(x_str)
plt.ylabel(y_str)
plt.title(title, fontsize=8)
plt.legend(loc='upper right', fancybox=True, shadow=True, prop={'size': 8})
plt.grid(True)
fig.savefig(path, bbox_inches='tight')
plt.close('all')
del fig
def plot(self, *args, **kwargs):
"""
Plot samples from the frequency distribution
displaying the most frequent sample first. If an integer
parameter is supplied, stop after this many samples have been
plotted. For a cumulative plot, specify cumulative=True.
(Requires Matplotlib to be installed.)
:param title: The title for the graph
:type title: str
:param cumulative: A flag to specify whether the plot is cumulative (default = False)
:type title: bool
"""
try:
from matplotlib import pylab
except ImportError:
raise ValueError('The plot function requires matplotlib to be installed.'
'See http://matplotlib.org/')
if len(args) == 0:
args = [len(self)]
samples = [item for item, _ in self.most_common(*args)]
cumulative = _get_kwarg(kwargs, 'cumulative', False)
if cumulative:
freqs = list(self._cumulative_frequencies(samples))
ylabel = "Cumulative Counts"
else:
freqs = [self[sample] for sample in samples]
ylabel = "Counts"
# percents = [f * 100 for f in freqs] only in ProbDist?
pylab.grid(True, color="silver")
if not "linewidth" in kwargs:
kwargs["linewidth"] = 2
if "title" in kwargs:
pylab.title(kwargs["title"])
del kwargs["title"]
pylab.plot(freqs, **kwargs)
pylab.xticks(range(len(samples)), [compat.text_type(s) for s in samples], rotation=90)
pylab.xlabel("Samples")
pylab.ylabel(ylabel)
pylab.show()