Diffusion solar_potential (master) Browse

make_shaded_area_features.py
c54246b01dfdmaster

make_shaded_area_features.py
View Options

			import numpy as np
			import pandas as pd
			import xarray as xr
			import os
			import time
			from features import Training, Testing
			from sklearn.model_selection import train_test_split

			def attach_col_to_table(table, new_table, merge_column, value_column, value_col_target = None, how = 'left'):

			# merge column in new_table with table
			merged_table = table.merge(new_table.loc[ :,[merge_column, value_column] ], on = merge_column, how = how)

			# change name of column if required
			if value_col_target is not None:
			merged_table = merged_table.rename( {value_column : value_col_target} , axis = 1)

			return merged_table

			## ========== USER INPUT ===================

			target_path = "/Users/alinawalch/Documents/EPFL/data/rooftops" # folder in which "datasets" exists

			ROOFTOP_FILE = '/Users/alinawalch/Documents/EPFL/data/rooftops/GVA_select_area8_buf30_merged.csv'
			SHADE_2m_FILE = '/Users/alinawalch/Documents/EPFL/data/rooftops/shading_images/visibility/shading_vis_40_2m.csv'
			SHADE_50cm_FILE = '/Users/alinawalch/Documents/EPFL/data/rooftops/shading_images/visibility/shading_vis_40_50cm.csv'

			# List of features and tables
			FEATURES = ['shaded_area_ratio_2m', 'NEIGUNG', 'AUSRICHTUN', 'FLAECHE', 'SHAPE_Leng', 'SHAPE_Ratio', 'GASTW', 'GBAUP', 'GAREA', 'n_neighbors_100']
			TARGETS = ['shaded_area_ratio_50cm']

			SAMPLE_SIZE = 1.0 # percentage of the data that is used for training & testing (THE SAMPLE)
			TEST_RATIO = 0.2 # percentage of the sample that is used for testing

			## === MERGE INFORMATION OF ROOFS & SHADING ==

			rooftops = pd.read_csv( ROOFTOP_FILE , index_col=0 )
			shade_2m = pd.read_csv( SHADE_2m_FILE , index_col=0 )
			shade_50cm = pd.read_csv( SHADE_50cm_FILE, index_col=0 )

			all_data = attach_col_to_table( rooftops, shade_2m , 'DF_UID', 'fully_shaded_ratio', 'shaded_area_ratio_2m' )
			all_data = attach_col_to_table( all_data, shade_50cm, 'DF_UID', 'fully_shaded_ratio', 'shaded_area_ratio_50cm' )

			# eliminate all duplicate columns and columns with NaNs:
			all_data_reduced = all_data.dropna().drop_duplicates()

			print("Created learning table with columns:")
			print(all_data_reduced.columns)

			## ======== CREATE NEW DATASET ==============

			# declare new training dataset
			modelname = ("fully_shaded_ratio_%dD" %len(FEATURES))
			new_set = Training(target_path, modelname, FEATURES, TARGETS, data_type = 'table')

			print(new_set.train_path) # this will contain both training and validation feature tables
			print(new_set.test_path)

			## ====== CREATE FEATURE AND TARGET TABLES ===

			# select the sample and split into training and testing data
			learning_table = all_data_reduced.sample( frac = SAMPLE_SIZE )
			train_table, test_table = train_test_split( learning_table, test_size = TEST_RATIO )

			# create the new dataset and normalize data
			new_set.make_dataset( table = train_table, test_table = test_table )
			new_set.normalize_all( val_ratio = 1.0 ) # DO NOT SPLIT into val and tr (for cross-validation purposes)

solarPOT/DOM/make_shaded_area_features.pyc54246b01dfdmaster

make_shaded_area_features.pyView Options

solarPOT/DOM/make_shaded_area_features.py
c54246b01dfdmaster

make_shaded_area_features.py
View Options