view notebooks/sensitivity_experiment_server_mapper.py @ 48:08b9327f1935 branch-tests

mapper now writes output

import numpy as np
import pandas as pd
import sys
sys.path.append('../')
import scripts.load_dataset as load_dataset
import scripts.map_and_average as mapper
import scripts.classification as classification
import scripts.outliers as outliers

#df = load_dataset.sample_dataset(csv_file=load_dataset.METADATA_FILE)
OUTPUT_FILES = load_dataset.OUTPUT_FILES
n_iters = 1
n = int(sys.argv[1])
MAPPER_OUTPUT_FILES = mapper.OUTPUT_FILES

#for n in range(n_iters):
if 1:
    print "iteration %d" % n
    
    print "mapping..."
    mapper.INPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for 
                                 output_file in OUTPUT_FILES]
    _, _, ldadata_list, _, _, Y, Yaudio = mapper.lda_map_and_average_frames(min_variance=0.99)
    mapper.OUTPUT_FILES = [output_file.split('.pickle')[0]+'_'+str(n)+'.pickle' for 
                                 output_file in MAPPER_OUTPUT_FILES]
    mapper.write_output([], [], ldadata_list, [], [], Y, Yaudio)
    
    #X = np.concatenate(ldadata_list, axis=1)
    
    ## classification and confusion
    #print "classifying..."
    #traininds, testinds = classification.get_train_test_indices(Yaudio)
    #X_train, Y_train, X_test, Y_test = classification.get_train_test_sets(X, Y, traininds, testinds)
    #accuracy, _ = classification.confusion_matrix(X_train, Y_train, X_test, Y_test, saveCF=False, plots=False)
    #print accuracy
    
    ## outliers
    #print "detecting outliers..."
    #df_global, threshold, MD = outliers.get_outliers_df(X, Y, chi2thr=0.999)
    #outliers.print_most_least_outliers_topN(df_global, N=10)
    
    ## write output
    #print "writing file"
    #df_global.to_csv('../data/outliers_'+str(n)+'.csv', index=False)