In [1]:
import glob
import numpy as np
import pandas as pd
from grafting_classifier import GraftingClassifier
from sklearn.linear_model import SGDClassifier
from ogfs_classifier import OGFSClassifier
from dpp_classifier import DPPClassifier
from dpp_classifier_mitra import DPPClassifier as DPPClassifier2
from dpp_classifier_dppsample import DPPClassifier as DPPClassifier0
from dpp_classifier_ogfs2 import DPPClassifier as DPPClassifier3
from sklearn.metrics import log_loss, accuracy_score
#import dask.dataframe as dd
#import dask.array as da
In [2]:
class_train = glob.glob("microarray/*_train.csv")
print(class_train)
In [3]:
def train_label(fname):
targetname = fname.replace(".csv", ".labels")
return pd.read_csv(targetname)
In [4]:
def get_performance(mod, fpath, base=False):
train1 = pd.read_csv(fpath).fillna(0)
y = np.array(train_label(fpath)).flatten()
# simulate streaming...
# try splitting into groups of ~10,
# if there is no splits, try ~5.
train1_cols = np.array_split(range(train1.shape[1]), min(10, int(train1.shape[1]/10.0) + 1))
if len(train1_cols) == 1:
train1_cols = np.array_split(range(train1.shape[1]), min(10, int(train1.shape[1]/5.0) + 1))
all_cols = []
#mod = GraftingClassifier(max_iter=5)
if base:
mod.fit(train1, y)
results = {'accuracy': accuracy_score(y, mod.predict(train1)),
'logloss': log_loss(y, mod.predict_proba(train1)),
'feat_dim': mod.coef_.flatten().shape}
return results
for idx, collist in enumerate(train1_cols):
if idx == 0:
column_list = list(np.array(list(train1.columns))[collist])
mod.fit(train1[column_list], y)
all_cols.extend(list(collist))
else:
all_cols.extend(list(collist))
column_list = list(np.array(list(train1.columns))[all_cols])
mod.partial_fit(train1[column_list], y)
results = {'accuracy': accuracy_score(y, mod.predict(train1)),
'logloss': log_loss(y, mod.predict_proba(train1)),
'feat_dim': mod.coef_.flatten().shape}
return results
In [5]:
models = [
#('Grafting', GraftingClassifier(max_iter=5, random_state=42)),
#('DPP', DPPClassifier(max_iter=5, random_state=42)),
('DPP', DPPClassifier3(max_iter=5, random_state=42)),
#('DPP2', DPPClassifier2(max_iter=5, random_state=42)),
#('OGFS', OGFSClassifier(max_iter=5, random_state=42)),
('Base', SGDClassifier(loss='log', max_iter=5, random_state=42))
]
In [6]:
class_train = glob.glob("microarray/*_train.csv")
print(class_train)
In [7]:
#ex_dat = class_train[0]
#print(ex_dat)
#for nm, mod in models:
# if nm != 'Base':
# print(nm, get_performance(mod, ex_dat))
# else:
# print(nm, get_performance(mod, ex_dat, base=True))
In [ ]:
ex_dat = class_train[1]
print(ex_dat)
print(pd.read_csv(ex_dat).shape)
for nm, mod in models:
if nm != 'Base':
print(nm, get_performance(mod, ex_dat))
else:
print(nm, get_performance(mod, ex_dat, base=True))
In [ ]:
ex_dat = class_train[2]
print(ex_dat)
for nm, mod in models:
if nm != 'Base':
print(nm, get_performance(mod, ex_dat))
else:
print(nm, get_performance(mod, ex_dat, base=True))
In [ ]:
ex_dat = class_train[3]
print(ex_dat)
for nm, mod in models:
if nm != 'Base':
print(nm, get_performance(mod, ex_dat))
else:
print(nm, get_performance(mod, ex_dat, base=True))