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.

Sign up for GitHub

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

Jump to bottom

Add a new parameter in the main function: outer_scaler #217

Open
wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Add a new parameter in the main function: outer_scaler #217

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
60abea0
Add a new parameter in the main function: outer_scaler, it is used to…
Larryliu912 Jul 24, 2018
230cf9d
Formed code to fit the flake8
Larryliu912 Jul 25, 2018
73f92d5
Reduced overlong lines
Larryliu912 Jul 25, 2018
9652284
overlong line fix
Larryliu912 Jul 25, 2018
f375c33
form improve
Larryliu912 Jul 25, 2018
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
Binary file added .DS_Store
View file
Open in desktop
Binary file not shown.
Binary file added lime/.DS_Store
View file
Open in desktop
Binary file not shown.
40 changes: 25 additions & 15 deletions lime/discretize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import sklearn.tree
from sklearn.utils import check_random_state
from abc import ABCMeta, abstractmethod
import copy


class BaseDiscretizer():
Expand All @@ -18,7 +19,8 @@ class BaseDiscretizer():

__metaclass__ = ABCMeta # abstract class

def __init__(self, data, categorical_features, feature_names, labels=None, random_state=None):
def __init__(self, data, categorical_features, feature_names,
labels=None, scaler=None, random_state=None):
"""Initializer
Args:
data: numpy 2d array
Expand All @@ -41,7 +43,7 @@ def __init__(self, data, categorical_features, feature_names, labels=None, rando
self.mins = {}
self.maxs = {}
self.random_state = check_random_state(random_state)

self.scaler = scaler
# To override when implementing a custom binning
bins = self.bins(data, labels)
bins = [np.unique(x) for x in bins]
Expand All @@ -50,13 +52,17 @@ def __init__(self, data, categorical_features, feature_names, labels=None, rando
n_bins = qts.shape[0] # Actually number of borders (= #bins-1)
boundaries = np.min(data[:, feature]), np.max(data[:, feature])
name = feature_names[feature]

self.names[feature] = ['%s <= %.2f' % (name, qts[0])]
# ADD: inverse transform output value back to the natural value
qts_cp = copy.deepcopy(qts)
if scaler is not None:
for i in range(n_bins):
dummy = np.zeros(len(bins))
dummy[feature] = qts[i]
qts_cp[i] = scaler.inverse_transform(dummy)[feature]
self.names[feature] = ['%s <= %.2f' % (name, qts_cp[0])]
for i in range(n_bins - 1):
self.names[feature].append('%.2f < %s <= %.2f' %
(qts[i], name, qts[i + 1]))
self.names[feature].append('%s > %.2f' % (name, qts[n_bins - 1]))

self.names[feature].append('%.2f < %s <= %.2f' % (qts_cp[i], name, qts_cp[i + 1]))
self.names[feature].append('%s > %.2f' % (name, qts_cp[n_bins - 1]))
self.lambdas[feature] = lambda x, qts=qts: np.searchsorted(qts, x)
discretized = self.lambdas[feature](data[:, feature])

Expand Down Expand Up @@ -107,7 +113,8 @@ def undiscretize(self, data):

def get_inverse(q):
return max(mins[q],
min(self.random_state.normal(means[q], stds[q]), maxs[q]))
min(self.random_state.normal(
means[q], stds[q]), maxs[q]))
if len(data.shape) == 1:
q = int(ret[feature])
ret[feature] = get_inverse(q)
Expand All @@ -118,11 +125,12 @@ def get_inverse(q):


class QuartileDiscretizer(BaseDiscretizer):
def __init__(self, data, categorical_features, feature_names, labels=None, random_state=None):
def __init__(self, data, categorical_features, feature_names,
labels=None, random_state=None, scaler=None):

BaseDiscretizer.__init__(self, data, categorical_features,
feature_names, labels=labels,
random_state=random_state)
random_state=random_state, scaler=scaler)

def bins(self, data, labels):
bins = []
Expand All @@ -133,10 +141,11 @@ def bins(self, data, labels):


class DecileDiscretizer(BaseDiscretizer):
def __init__(self, data, categorical_features, feature_names, labels=None, random_state=None):
def __init__(self, data, categorical_features, feature_names,
labels=None, random_state=None, scaler=None):
BaseDiscretizer.__init__(self, data, categorical_features,
feature_names, labels=labels,
random_state=random_state)
random_state=random_state, scaler=scaler)

def bins(self, data, labels):
bins = []
Expand All @@ -148,13 +157,14 @@ def bins(self, data, labels):


class EntropyDiscretizer(BaseDiscretizer):
def __init__(self, data, categorical_features, feature_names, labels=None, random_state=None):
def __init__(self, data, categorical_features, feature_names,
labels=None, random_state=None, scaler=None):
if(labels is None):
raise ValueError('Labels must be not None when using \
EntropyDiscretizer')
BaseDiscretizer.__init__(self, data, categorical_features,
feature_names, labels=labels,
random_state=random_state)
random_state=random_state, scaler=scaler)

def bins(self, data, labels):
bins = []
Expand Down
28 changes: 18 additions & 10 deletions lime/lime_tabular.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ class TableDomainMapper(explanation.DomainMapper):
"""Maps feature ids to names, generates table views, etc"""

def __init__(self, feature_names, feature_values, scaled_row,
categorical_features, discretized_feature_names=None):
categorical_features, discretized_feature_names=None, outer_scaler=None):
"""Init.

Args:
Expand All @@ -39,6 +39,7 @@ def __init__(self, feature_names, feature_values, scaled_row,
self.scaled_row = scaled_row
self.all_categorical = len(categorical_features) == len(scaled_row)
self.categorical_features = categorical_features
self.outer_scaler = outer_scaler

def map_exp_ids(self, exp):
"""Maps ids to feature names.
Expand Down Expand Up @@ -76,8 +77,14 @@ def visualize_instance_html(self,
weights = [0] * len(self.feature_names)
for x in exp:
weights[x[0]] = x[1]
# ADD: inverse transform output value back to the natural value
outer_scaler = self.outer_scaler
outer_value = self.feature_values
if outer_scaler is not None:
outer_list = list(map(float, self.feature_values[0:6]))
outer_value[0:6] = outer_scaler.inverse_transform(outer_list).round()
out_list = list(zip(self.exp_feature_names,
self.feature_values,
outer_value,
weights))
if not show_all:
out_list = [out_list[x[0]] for x in exp]
Expand Down Expand Up @@ -110,7 +117,8 @@ def __init__(self,
discretize_continuous=True,
discretizer='quartile',
sample_around_instance=False,
random_state=None):
random_state=None,
outer_scaler=None):
"""Init function.

Args:
Expand Down Expand Up @@ -153,7 +161,7 @@ def __init__(self,
self.mode = mode
self.categorical_names = categorical_names or {}
self.sample_around_instance = sample_around_instance

self.outer_scaler = outer_scaler
if categorical_features is None:
categorical_features = []
if feature_names is None:
Expand All @@ -167,15 +175,15 @@ def __init__(self,
if discretizer == 'quartile':
self.discretizer = QuartileDiscretizer(
training_data, self.categorical_features,
self.feature_names, labels=training_labels)
self.feature_names, labels=training_labels, scaler=self.outer_scaler)
elif discretizer == 'decile':
self.discretizer = DecileDiscretizer(
training_data, self.categorical_features,
self.feature_names, labels=training_labels)
self.feature_names, labels=training_labels, scaler=self.outer_scaler)
elif discretizer == 'entropy':
self.discretizer = EntropyDiscretizer(
training_data, self.categorical_features,
self.feature_names, labels=training_labels)
self.feature_names, labels=training_labels, scaler=self.outer_scaler)
elif isinstance(discretizer, BaseDiscretizer):
self.discretizer = discretizer
else:
Expand Down Expand Up @@ -262,9 +270,9 @@ def explain_instance(self,
An Explanation object (see explanation.py) with the corresponding
explanations.
"""
outer_scaler = self.outer_scaler
data, inverse = self.__data_inverse(data_row, num_samples)
scaled_data = (data - self.scaler.mean_) / self.scaler.scale_

distances = sklearn.metrics.pairwise_distances(
scaled_data,
scaled_data[0].reshape(1, -1),
Expand Down Expand Up @@ -342,7 +350,8 @@ def explain_instance(self,
values,
scaled_data[0],
categorical_features=categorical_features,
discretized_feature_names=discretized_feature_names)
discretized_feature_names=discretized_feature_names,
outer_scaler=outer_scaler)
ret_exp = explanation.Explanation(domain_mapper,
mode=self.mode,
class_names=self.class_names)
Expand Down Expand Up @@ -370,7 +379,6 @@ def explain_instance(self,
num_features,
model_regressor=model_regressor,
feature_selection=self.feature_selection)

if self.mode == "regression":
ret_exp.intercept[1] = ret_exp.intercept[0]
ret_exp.local_exp[1] = [x for x in ret_exp.local_exp[0]]
Expand Down