In [44]:

    

import glob

import numpy as np
import pandas as pd

from grafting_classifier import GraftingClassifier
from sklearn.linear_model import SGDClassifier

from sklearn.metrics import log_loss, accuracy_score

#import dask.dataframe as dd
#import dask.array as da


    

In [32]:

    

class_train = glob.glob("microarray/*_train.csv")
print(class_train)


    

    




['microarray\\colon_train.csv', 'microarray\\leukemia_train.csv', 'microarray\\lung_cancer_train.csv', 'microarray\\prostate_train.csv']

In [33]:

    

def train_label(fname):
    targetname = fname.replace(".csv", ".labels")
    return pd.read_csv(targetname)


    

In [34]:

    

fpath = class_train[3]
train1 = pd.read_csv(fpath).fillna(0)
y = np.array(train_label(fpath)).flatten()
train1_cols = np.array_split(range(train1.shape[1]), int(train1.shape[1]/10.0) + 1)
all_cols = []

mod = GraftingClassifier(max_iter=5)

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)


    

In [35]:

    

"target" in list(train1.columns)


    

    
Out[35]:





False

In [36]:

    

"y" in list(train1.columns)


    

    
Out[36]:





False

In [37]:

    

train1.shape


    

    
Out[37]:





(102, 12600)

In [38]:

    

y.shape


    

    
Out[38]:





(102,)

In [39]:

    

accuracy_score(y, mod.predict(train1))


    

    
Out[39]:





1.0

In [40]:

    

log_loss(y, mod.predict(train1))


    

    
Out[40]:





16.931164702127877

In [41]:

    

train1.shape


    

    
Out[41]:





(102, 12600)

In [42]:

    

mod.coef_.flatten().shape


    

    
Out[42]:





(1306,)

In [45]:

    

mod_base = SGDClassifier(loss='log', max_iter=5)
mod_base.fit(train1, y)

print("Accuracy: {}".format(accuracy_score(y, mod_base.predict(train1))))
print("Logloss: {}".format(log_loss(y, mod_base.predict(train1))))


    

    




Accuracy: 0.9803921568627451
Logloss: 16.931164702127877