from Conf.Settings import ASD_PATH, ASD_DW_PATH, ASD_DW_RESULTS_PATH, MIN_D_N, MAX_LAG, CUT_OFF, TYPICAL_PATH, \
TYPICAL_DW_PATH, TYPICAL_DW_RESULTS_PATH, AVG_WIN_SIZE, FREQ_GAZE, AREA_FIX_TH
from Utils.Lib import filterFixation
import matplotlib.pyplot as plt
from nolds import sampen
from sklearn.neighbors import KernelDensity
import warnings
# set the processing
# ASD or TYPICAL
game_paths = [TYPICAL_PATH, ASD_PATH]
gaze_paths = [TYPICAL_DW_PATH, ASD_DW_PATH]
result_paths = [TYPICAL_DW_RESULTS_PATH, ASD_DW_RESULTS_PATH]
# Reader and removal
reader = DataReader()
removal = OutliersRemoval(cutoff=CUT_OFF)
# edges
xedges, yedges = np.arange(0, 101, 1), np.arange(0, 101, 1)
# x_grid, y_grid = np.mgrid[0:1:100j, 0:1:100j]
# positions = np.vstack([x_grid.ravel(), y_grid.ravel()])
for path in zip(game_paths, gaze_paths, result_paths):
game_path = path[0]
gaze_path = path[1]
result_path = path[2]
# read game data
data_game, game_f_names = reader.readGameResults(game_path)
data_game = removal.transformGameResult(
################################## IMPORTS ################################## from Utils.SearchAbstractClass import SearchInputRecommenderArgs from Utils.SearchBayesianSkopt import SearchBayesianSkopt from skopt.space import Real, Integer, Categorical from Utils.Evaluator import EvaluatorHoldout from Utils.DataSplitter import DataSplitter from Utils.DataReader import DataReader import os # Model to be tuned from hybrid import Hybrid ################################# READ DATA ################################# reader = DataReader() splitter = DataSplitter() urm = reader.load_urm() ICM = reader.load_icm() URM_train, URM_val, URM_test = splitter.split(urm, validation=0.2, testing=0.1) ################################ EVALUATORS ################################## evaluator_validation = EvaluatorHoldout(URM_val, [10]) evaluator_test = EvaluatorHoldout(URM_test, [10]) ############################### OPTIMIZER SETUP ############################### recommender_class = Hybrid parameterSearch = SearchBayesianSkopt(
def test_dataReader(self):
reader = DataReader()
removal = OutliersRemoval(cutoff=150)
data_game, _ = reader.readGameResults(ASD_PATH)
data_gaze, _, _ = reader.readGazeData(ASD_PATH)
self.assertEqual(len(data_game), len(data_gaze))
def fit(self,
topK=50,
shrink=100,
similarity='cosine',
normalization="none",
feature_weighting="none",
**similarity_args):
self.topK = topK
self.shrink = shrink
reader = DataReader()
icm = reader.load_icm()
if normalization == "bm25":
self.URM_train = similaripy.normalization.bm25(self.URM_train,
axis=1)
if normalization == "tfidf":
self.URM_train = similaripy.normalization.tfidf(self.URM_train,
axis=1)
if normalization == "bm25plus":
self.URM_train = similaripy.normalization.bm25plus(self.URM_train,
axis=1)
if feature_weighting == "bm25":
icm = similaripy.normalization.bm25(icm, axis=1)
if feature_weighting == "tfidf":
icm = similaripy.normalization.tfidf(icm, axis=1)
if feature_weighting == "bm25plus":
icm = similaripy.normalization.bm25plus(icm, axis=1)
matrix = sps.hstack((self.URM_train.transpose().tocsr(), icm))
if similarity == "cosine":
similarity_matrix = similaripy.cosine(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "dice":
similarity_matrix = similaripy.dice(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "jaccard":
similarity_matrix = similaripy.jaccard(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "asym":
similarity_matrix = similaripy.asymmetric_cosine(
matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0)
if similarity == "rp3beta":
similarity_matrix = similaripy.rp3beta(matrix,
k=self.topK,
shrink=self.shrink,
binary=False,
threshold=0,
alpha=0.3,
beta=0.61)
self.W_sparse = similarity_matrix
self.W_sparse = check_matrix(self.W_sparse, format='csr')
################################## IMPORTS ##################################
from Utils.Evaluator import EvaluatorHoldout
from Utils.DataSplitter import DataSplitter
from Utils.DataReader import DataReader
from hybrid import Hybrid
from tqdm import tqdm
################################# READ DATA #################################
reader = DataReader()
splitter = DataSplitter()
urm = reader.load_urm()
ICM = reader.load_icm()
targets = reader.load_target()
URM_train, URM_val, URM_test = splitter.split(urm, validation=0, testing=0)
####################### ISTANTIATE AND FIT THE HYBRID #######################
recommender = Hybrid(URM_train, ICM)
recommender.fit()
################################ PRODUCE CSV ################################
f = open("submission.csv", "w+")
f.write("user_id,item_list\n")
for t in tqdm(targets):
recommended_items = recommender.recommend(t, cutoff=10, remove_seen_flag=True)
well_formatted = " ".join([str(x) for x in recommended_items])
f.write(f"{t}, {well_formatted}\n")
import glob import numpy as np from Utils.DataReader import DataReader from Utils.Lib import arParams, createDir from Utils.OutliersRemoval import OutliersRemoval from Conf.Settings import ASD_PATH, ASD_DW_PATH, MIN_D_N, CUT_OFF, TYPICAL_PATH, TYPICAL_DW_PATH from scipy import interpolate from statsmodels.tsa.ar_model import AR max_lag = np.zeros(20) max_llf = np.zeros(20) aic_lag = np.zeros(20) bic_lag = np.zeros(20) # read game data reader = DataReader() removal = OutliersRemoval(cutoff=CUT_OFF) # read typical data typical_game, _ = reader.readGameResults(TYPICAL_PATH) typical_game = removal.transformGameResult(typical_game) _, typical_gaze_obj, _ = reader.readGazeData(TYPICAL_DW_PATH, downsample=True) # read asd data asd_game, _ = reader.readGameResults(ASD_PATH) asd_game = removal.transformGameResult(asd_game) _, asd_gaze_obj, _ = reader.readGazeData(ASD_DW_PATH, downsample=True) data_game = typical_game + asd_game data_gaze = typical_gaze_obj + asd_gaze_obj for d in zip(data_game, data_gaze):
"""
Created on 06/05/2018
@author Stefan
"""
from Domain.Network import Network
from Utils.DataReader import DataReader
if __name__ == '__main__':
dr = DataReader()
net = Network(21, 3, 2, 10)
net.learning(dr.learningData)
net.testing(dr.testData)