#!/usr/bin/env python
import json
from algos.LogisticRegression import LogisticRegression
from sklearn.linear_model import LogisticRegression as _LogisticRegression
from util.param_util import convert_params, is_truthy
from codec import codecs_manager
from cexc import get_messages_logger
messages = get_messages_logger()
class MultinomialLogisticRegression(LogisticRegression):
def __init__(self, options):
self.handle_options(options)
out_params = convert_params(
options.get('params', {}),
bools=['fit_intercept', 'probabilities'],
strs=['solver', 'multi_class', 'class_weight'])
# Solver
if 'solver' in out_params:
if out_params['solver'] not in ['newton-cg', 'lbfgs']:
raise RuntimeError('solver must be either: newton-cg or lbfgs')
else:
# default
out_params['solver'] = 'newton-cg'
# Multiclass
# Copyright (C) 2015-2017 Splunk Inc. All Rights Reserved.
import errno
import gc
import os
import pandas as pd
import cexc
import conf
import models.base
from BaseProcessor import BaseProcessor
from util import search_util
logger = cexc.get_logger(__name__)
messages = cexc.get_messages_logger()
class ApplyProcessor(BaseProcessor):
"""The apply processor receives and returns pandas DataFrames."""
def __init__(self, process_options, searchinfo):
"""Initialize options for the processor.
Args:
process_options (dict): process options
searchinfo (dict): information required for search
"""
self.searchinfo = searchinfo
self.algo_name, self.algo, self.process_options, self.namespace = self.setup_model(process_options, self.searchinfo)
self.resource_limits = self.load_resource_limits(self.algo_name)
#!/usr/bin/env python
from base import BaseAlgo, TransformerMixin
from codec import codecs_manager
from util.param_util import convert_params
import pandas as pd
import networkx as nx
from cexc import get_messages_logger, get_logger
debug = get_messages_logger()
class GraphLabelPropagation(TransformerMixin, BaseAlgo):
def __init__(self, options):
debug.info('NetworkX Version {}'.format(nx.__version__))
self.handle_options(options)
# call same logic as in fit
def apply(self, df, options):
return self.fit(df, options)
# compute connected components
def fit(self, df, options):
# Make a copy of data, to not alter original dataframe
X = df.copy()
# create a directed graph
graph = nx.Graph()
src_dest_name = self.feature_variables
dfg = X[src_dest_name]
for index, row in dfg.iterrows():
graph.add_edge(row[src_dest_name[0]],
row[src_dest_name[1]]) #, value=row['value'])
