Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Esa team #143

Merged
merged 3 commits into from
Jan 26, 2017
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
187 changes: 187 additions & 0 deletions esaTeam/classification_utilities.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,187 @@
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.colors as colors
from mpl_toolkits.axes_grid1 import make_axes_locatable


def display_cm(cm, labels, hide_zeros=False,
display_metrics=False):
"""Display confusion matrix with labels, along with
metrics such as Recall, Precision and F1 score.
Based on Zach Guo's print_cm gist at
https://gist.github.com/zachguo/10296432
"""

precision = np.diagonal(cm)/cm.sum(axis=0).astype('float')
recall = np.diagonal(cm)/cm.sum(axis=1).astype('float')
F1 = 2 * (precision * recall) / (precision + recall)

precision[np.isnan(precision)] = 0
recall[np.isnan(recall)] = 0
F1[np.isnan(F1)] = 0

total_precision = np.sum(precision * cm.sum(axis=1)) / cm.sum(axis=(0,1))
total_recall = np.sum(recall * cm.sum(axis=1)) / cm.sum(axis=(0,1))
total_F1 = np.sum(F1 * cm.sum(axis=1)) / cm.sum(axis=(0,1))
#print total_precision

columnwidth = max([len(x) for x in labels]+[5]) # 5 is value length
empty_cell = " " * columnwidth
# Print header
print(" " + " Pred", end=' ')
for label in labels:
print("%{0}s".format(columnwidth) % label, end=' ')
print("%{0}s".format(columnwidth) % 'Total')
print(" " + " True")
# Print rows
for i, label1 in enumerate(labels):
print(" %{0}s".format(columnwidth) % label1, end=' ')
for j in range(len(labels)):
cell = "%{0}d".format(columnwidth) % cm[i, j]
if hide_zeros:
cell = cell if float(cm[i, j]) != 0 else empty_cell
print(cell, end=' ')
print("%{0}d".format(columnwidth) % sum(cm[i,:]))

if display_metrics:
print()
print("Precision", end=' ')
for j in range(len(labels)):
cell = "%{0}.2f".format(columnwidth) % precision[j]
print(cell, end=' ')
print("%{0}.2f".format(columnwidth) % total_precision)
print(" Recall", end=' ')
for j in range(len(labels)):
cell = "%{0}.2f".format(columnwidth) % recall[j]
print(cell, end=' ')
print("%{0}.2f".format(columnwidth) % total_recall)
print(" F1", end=' ')
for j in range(len(labels)):
cell = "%{0}.2f".format(columnwidth) % F1[j]
print(cell, end=' ')
print("%{0}.2f".format(columnwidth) % total_F1)


def display_adj_cm(
cm, labels, adjacent_facies, hide_zeros=False,
display_metrics=False):
"""This function displays a confusion matrix that counts
adjacent facies as correct.
"""
adj_cm = np.copy(cm)

for i in np.arange(0,cm.shape[0]):
for j in adjacent_facies[i]:
adj_cm[i][i] += adj_cm[i][j]
adj_cm[i][j] = 0.0

display_cm(adj_cm, labels, hide_zeros,
display_metrics)


def make_facies_log_plot(logs, facies_colors):
#make sure logs are sorted by depth
logs = logs.sort_values(by='Depth')
cmap_facies = colors.ListedColormap(
facies_colors[0:len(facies_colors)], 'indexed')

ztop=logs.Depth.min(); zbot=logs.Depth.max()

cluster=np.repeat(np.expand_dims(logs['Facies'].values,1), 100, 1)

f, ax = plt.subplots(nrows=1, ncols=6, figsize=(8, 12))
ax[0].plot(logs.GR, logs.Depth, '-g')
ax[1].plot(logs.ILD_log10, logs.Depth, '-')
ax[2].plot(logs.DeltaPHI, logs.Depth, '-', color='0.5')
ax[3].plot(logs.PHIND, logs.Depth, '-', color='r')
ax[4].plot(logs.PE, logs.Depth, '-', color='black')
im=ax[5].imshow(cluster, interpolation='none', aspect='auto',
cmap=cmap_facies,vmin=1,vmax=9)

divider = make_axes_locatable(ax[5])
cax = divider.append_axes("right", size="20%", pad=0.05)
cbar=plt.colorbar(im, cax=cax)
cbar.set_label((17*' ').join([' SS ', 'CSiS', 'FSiS',
'SiSh', ' MS ', ' WS ', ' D ',
' PS ', ' BS ']))
cbar.set_ticks(range(0,1)); cbar.set_ticklabels('')

for i in range(len(ax)-1):
ax[i].set_ylim(ztop,zbot)
ax[i].invert_yaxis()
ax[i].grid()
ax[i].locator_params(axis='x', nbins=3)

ax[0].set_xlabel("GR")
ax[0].set_xlim(logs.GR.min(),logs.GR.max())
ax[1].set_xlabel("ILD_log10")
ax[1].set_xlim(logs.ILD_log10.min(),logs.ILD_log10.max())
ax[2].set_xlabel("DeltaPHI")
ax[2].set_xlim(logs.DeltaPHI.min(),logs.DeltaPHI.max())
ax[3].set_xlabel("PHIND")
ax[3].set_xlim(logs.PHIND.min(),logs.PHIND.max())
ax[4].set_xlabel("PE")
ax[4].set_xlim(logs.PE.min(),logs.PE.max())
ax[5].set_xlabel('Facies')

ax[1].set_yticklabels([]); ax[2].set_yticklabels([]); ax[3].set_yticklabels([])
ax[4].set_yticklabels([]); ax[5].set_yticklabels([])
ax[5].set_xticklabels([])
f.suptitle('Well: %s'%logs.iloc[0]['Well Name'], fontsize=14,y=0.94)


def compare_facies_plot(logs, compadre, facies_colors):
#make sure logs are sorted by depth
logs = logs.sort_values(by='Depth')
cmap_facies = colors.ListedColormap(
facies_colors[0:len(facies_colors)], 'indexed')

ztop=logs.Depth.min(); zbot=logs.Depth.max()

cluster1 = np.repeat(np.expand_dims(logs['Facies'].values,1), 100, 1)
cluster2 = np.repeat(np.expand_dims(logs[compadre].values,1), 100, 1)

f, ax = plt.subplots(nrows=1, ncols=7, figsize=(9, 12))
ax[0].plot(logs.GR, logs.Depth, '-g')
ax[1].plot(logs.ILD_log10, logs.Depth, '-')
ax[2].plot(logs.DeltaPHI, logs.Depth, '-', color='0.5')
ax[3].plot(logs.PHIND, logs.Depth, '-', color='r')
ax[4].plot(logs.PE, logs.Depth, '-', color='black')
im1 = ax[5].imshow(cluster1, interpolation='none', aspect='auto',
cmap=cmap_facies,vmin=1,vmax=9)
im2 = ax[6].imshow(cluster2, interpolation='none', aspect='auto',
cmap=cmap_facies,vmin=1,vmax=9)

divider = make_axes_locatable(ax[6])
cax = divider.append_axes("right", size="20%", pad=0.05)
cbar=plt.colorbar(im2, cax=cax)
cbar.set_label((17*' ').join([' SS ', 'CSiS', 'FSiS',
'SiSh', ' MS ', ' WS ', ' D ',
' PS ', ' BS ']))
cbar.set_ticks(range(0,1)); cbar.set_ticklabels('')

for i in range(len(ax)-2):
ax[i].set_ylim(ztop,zbot)
ax[i].invert_yaxis()
ax[i].grid()
ax[i].locator_params(axis='x', nbins=3)

ax[0].set_xlabel("GR")
ax[0].set_xlim(logs.GR.min(),logs.GR.max())
ax[1].set_xlabel("ILD_log10")
ax[1].set_xlim(logs.ILD_log10.min(),logs.ILD_log10.max())
ax[2].set_xlabel("DeltaPHI")
ax[2].set_xlim(logs.DeltaPHI.min(),logs.DeltaPHI.max())
ax[3].set_xlabel("PHIND")
ax[3].set_xlim(logs.PHIND.min(),logs.PHIND.max())
ax[4].set_xlabel("PE")
ax[4].set_xlim(logs.PE.min(),logs.PE.max())
ax[5].set_xlabel('Facies')
ax[6].set_xlabel(compadre)

ax[1].set_yticklabels([]); ax[2].set_yticklabels([]); ax[3].set_yticklabels([])
ax[4].set_yticklabels([]); ax[5].set_yticklabels([])
ax[5].set_xticklabels([])
ax[6].set_xticklabels([])
f.suptitle('Well: %s'%logs.iloc[0]['Well Name'], fontsize=14,y=0.94)
Loading