def sort_dataframe(df_data, df_filenames):
correct_order = Input.load_testdata_filenames()
current_order = list(df_filenames.values)
indices = [current_order.index(filename) for filename in correct_order]
df_data = df_data.reindex(indices)
df_data = df_data.reset_index() #reset index --> adds new indices, old indices become column 'index'
return df_data.drop('index', axis=1) #remove this new column 'index'
import numpy as np
from IO import Output
import pickle
from sklearn.svm import LinearSVC
'''
Helper function to use with the grouping of the dataframe, turns 3 rows of coordinates into a single row
'''
def transformXY(coords):
return pd.Series(np.asarray(coords).ravel())
#Load the file names of the various datasets
trainset_filenames = Input.load_trainset_filenames()
validationset_filenames = Input.load_validationset_filenames()
traindata_filenames = Input.load_traindata_filenames()
testset_filenames = Input.load_testdata_filenames()
#Load the features
feat = pd.read_csv('skinTrainFeatures.csv', index_col = 0)
#Select the features for each dataset
x_trainset = feat.ix[trainset_filenames]
x_validationset = feat.ix[validationset_filenames]
x_testset = feat.ix[testset_filenames]
x_traindata = feat.ix[traindata_filenames]
#Load the labels for each dataset
y_trainset = np.asarray(Input.load_trainset_labels())
y_validationset = np.asarray(Input.load_validationset_labels())
y_traindata = np.asarray(Input.load_traindata_labels())