def select_top_features(train_data):
fs = FeatureSelector(train_data[0], train_data[1])
fs.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=6,
early_stopping=True)
fs.identify_low_importance(cumulative_importance=0.99)
return fs.ops['zero_importance'], fs.ops['low_importance']
def featureselect(datas, target):
import os
os.chdir('c:\\Users\\SA\\python\\練習py')
from feature_selector import FeatureSelector
fs = FeatureSelector(data=datas, labels=target)
fs.identify_missing(missing_threshold=0.6)
fs.identify_collinear(correlation_threshold=0.9)
fs.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=10,
early_stopping=False)
fs.identify_low_importance(cumulative_importance=0.9)
train_removed = fs.remove(methods='all')
return train_removed
def Bestfeature_from_cummulative_importance(inFile, outFile):
df = pd.read_csv(inFile, sep='\t')
print(df.shape)
train_labels = df['class_label']
train = df.drop(columns=['class_label'])
fs = FeatureSelector(data=train, labels=train_labels)
fs.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=10,
early_stopping=True)
zero_importance_features = fs.ops['zero_importance']
#fs.plot_feature_importances(threshold = 0.99, plot_n = 12)
importance_index = np.min(
np.where(fs.feature_importances['cumulative_importance'] > 0.99))
fs.identify_low_importance(cumulative_importance=0.99)
print(importance_index)
train_removed_all = fs.remove(methods=['zero_importance'],
keep_one_hot=False)
train_removed_all = pd.concat([train_removed_all, train_labels], axis=1)
train_removed_all.to_csv(outFile, sep='\t', index=None)
def runFeatureSelector(self, df):
logging.info(("Running Feature Selection"))
fs = FeatureSelector(data=df, labels=self.targets)
# Identify Missing Values
fs.identify_missing(missing_threshold=0.6)
# Identify Collinearity
fs.identify_collinear(correlation_threshold=0.98)
fs.record_collinear.to_csv(".\\utils\\csv\\record_collinear.csv")
# Identify Single Unique
fs.identify_single_unique()
fs.record_single_unique.to_csv(
".\\utils\\csv\\record_single_unique.csv")
# Zero importance
fs.identify_zero_importance(task='classification',
eval_metric='multi_logloss',
n_iterations=10,
early_stopping=True)
fs.record_zero_importance.to_csv(
".\\utils\\csv\\record_zero_importance.csv")
# Low Importance
fs.identify_low_importance(cumulative_importance=0.99)
fs.feature_importances.to_csv(".\\utils\\csv\\feature_importance.csv")
#generate summary of all operations
summary = pd.DataFrame.from_dict(fs.ops, orient='index')
summary.to_csv(".\\utils\\csv\\summary.csv")
#if drop flag is 1, go ahead and remove the suggested features
if self.drop == 1:
df = fs.remove(methods='all')
else:
pass
return df
def remove_unnecessary_features(self, auto=False):
if auto:
self.processed_data = self.processed_data.drop(
columns=self.predefined_skip_features)
else:
fs = FeatureSelector(data=self.processed_data.drop("label",
axis=1),
labels=self.processed_data["label"])
fs.identify_missing(missing_threshold=0.6)
fs.identify_collinear(correlation_threshold=0.98)
fs.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=10,
early_stopping=False)
fs.identify_low_importance(cumulative_importance=0.99)
fs.identify_single_unique()
# Remove the features from all methods (returns a df)
labels = self.processed_data["label"]
self.processed_data = fs.remove(methods='all')
self.processed_data["label"] = labels
def select_best_features(data_file_path, saveto_path="Default"):
mod_data_file_path = strip_header(data_file_path)
if saveto_path == "Default":
saveto_path = replace_ext(data_file_path, '_reduced.csv')
X = pd.read_csv(mod_data_file_path)
y = X['Label']
X = X.drop(columns=['Label'])
feature_selector = FeatureSelector(data=X, labels=y)
feature_selector.identify_single_unique()
feature_selector.identify_collinear(correlation_threshold=0.98)
feature_selector.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=10,
early_stopping=True)
features_1hot = feature_selector.one_hot_features
features_base = feature_selector.base_features
feature_selector.identify_low_importance(cumulative_importance=0.99)
X_dash = feature_selector.remove(methods=[
'single_unique', 'collinear', 'zero_importance', 'low_importance'
],
keep_one_hot=False)
X_dash['Label'] = y
X_dash.to_csv(saveto_path, index=False)
meta_data = [str(X_dash.shape[0]), str(X_dash.shape[1] - 1)]
with open(saveto_path, 'r') as fh:
contents = fh.read()
contents = ','.join(meta_data) + '\n' + contents
with open(saveto_path, 'w') as fh:
fh.write(contents)
os.system("rm -f " + mod_data_file_path)
print(zero_importance_features[1:15])
fs.plot_feature_importances(threshold=0.99, plot_n=12)
plt.show()
print(fs.feature_importances.head(10))
one_hundred_features = list(fs.feature_importances.loc[:99, 'feature'])
len(one_hundred_features)
# 5. Low Importance Features
# When using this method, we must have already run identify_zero_importance and
# need to pass in a cumulative_importance that accounts for that fraction of total feature importance.
fs.identify_low_importance(cumulative_importance=0.99)
low_importance_features = fs.ops['low_importance']
print(low_importance_features[:5])
fs.plot_feature_importances(threshold=0.99, plot_n=12)
plt.show()
# 6 Removing Features
# Removing Features: This method returns the resulting data which we can then use for machine learning.
# The original data will still be accessible in the data attribute of the Feature Selector.
train_no_missing = fs.remove(methods=['missing']) #以鉴别17种
train_no_missing_zero = fs.remove(methods=['missing',
'zero_importance']) #已经鉴别66+17=83种
FeatureSelector.identify_feat_imp=identify_feat_imp # In[28]: fsDataScale.identify_feat_imp() # zero feath with 0 # In[29]: fsDataScale.identify_low_importance(0.95) # In[30]: fsDataScale.plot_feature_importances(plot_n=300) # In[31]: max(fsDataScale.scores) # In[32]:
fc.missing_stats.head()
# In[12]:
fc.identify_collinear(correlation_threshold=0.98)
# In[17]:
fc.identify_zero_importance(task='classification',
eval_metric='auc',
n_iterations=10,
early_stopping=True)
# In[18]:
fc.identify_low_importance(cumulative_importance=0.95)
# In[19]:
fc.identify_single_unique()
# In[30]:
train_removed = fc.remove(methods='all')
# In[31]:
np.save('train_removed2', train_removed.values)
# In[29]: