print(message) output.write(message) output.write("\n") output.flush() all_features = ['hour', 'day_of_week', 'month', 'bank_holiday', 'race_day', 'winddirection', 'windspeed', 'temperature', 'rain', 'pressure', 'atc', 'lane_length', 'length', 'landuse_area', 'leisure_area', 'buildings_area', 'buildings_number'] topTags = ['TW','TWA', 'TWL', 'WA'] topPreds = ["pred_" + tag for tag in topTags] locations = [2.0, 3.0, 4.0, 6.0, 8.0] all_columns = all_features + topPreds topDatagroups = [] data_groups = generateAllDataGroups() for tag in topTags: for datagroup in data_groups: dgtag, _ = getTagAndFeatures(datagroup) if dgtag == tag: topDatagroups.append(datagroup) break def evalColumns(columns): overallY = [] overallPred = [] for location in locations: location2s = [l for l in locations if l != location]
output.write("\n") for i in range(0, len(data)): if isinstance(data[i], list): for j in range(0, len(data[i])): if j != 0: output.write(",") output.write(str(data[i][j])) else: output.write(str(data[i])) output.write("\n") output.close() top16datagroups = [] data_groups = generateAllDataGroups() for tag in top16tags: for datagroup in data_groups: dgtag, _ = getTagAndFeatures(datagroup) if dgtag == tag: top16datagroups.append(datagroup) break all_tags, all_features = getTagAndFeatures(['T', 'W', 'A', 'R', 'L', 'B']) for location in locations: print("Location: " + str(location)) trainX1, trainX2, trainY1, trainY2, testX, testY = splitDataForXValidationSampled( location, "location", sampleRate, 42, data, all_features, "target") writeOutData(OUTPUT_DIRECTORY + "z_" + str(int(location)) + "_trainX.csv",