#Define meta list and properties that will store optimal networks results = [] results_header = [] #Start looping the columns; e.g., year 2000, then 2001, then 2002 for column in arange(len(data.columns.values)): current = data.columns.values[column] print("") print("Starting {0}".format(current)) #Find none blank values and assign them in list distribution purely to get the zeta values in default 'D' mode if zeta_type != 'S' and zeta_type != 'M': from NFA_zeta import zeta_default zeta_list = zeta_default(pd.to_numeric(data.ix[:,column]).dropna()) #Define list to store all the temporarily results for the current column temp_results = [] #Compute, store, and save all networks for list of zeta coefficients for i in arange(len(zeta_list)): temp_results.append(network_calc(pd.to_numeric(data.ix[:,column]).dropna(), zeta_list[i], column)) if record_all == 'Y': temp_zeta = [temp_results[i][1]] temp_zeta_current = int(current) save_individual_results(temp_results[i], temp_results[i][1], file_name, current) plot_final_network(temp_results[i], temp_results[i][1], file_name, current, x_label, coef_show, column_name, mode_value, x_scale, y_scale, x_limits1, x_limits2, y_limits1, y_limits2, grid_lines) #Determine "optimal" network giant_size = []
grid_lines = "" #Define meta list and properties that will store optimal networks results = [] results_header = [] #Start looping the columns; e.g., year 2000, then 2001, then 2002 for column in arange(len(data.columns.values)): current = data.columns.values[column] print("") print("Starting {0}".format(current)) #Find none blank values and assign them in list distribution purely to get the zeta values in default 'D' mode if zeta_type != 'S' and zeta_type != 'M': from NFA_zeta import zeta_default zeta_list = zeta_default(pd.to_numeric(data.ix[:, column]).dropna()) #Define list to store all the temporarily results for the current column temp_results = [] #Compute, store, and save all networks for list of zeta coefficients for i in arange(len(zeta_list)): temp_results.append( network_calc( pd.to_numeric(data.ix[:, column]).dropna(), zeta_list[i], column)) if record_all == 'Y': temp_zeta = [temp_results[i][1]] temp_zeta_current = int(current) save_individual_results(temp_results[i], temp_results[i][1], file_name, current)
grid_lines = "" #Define meta list and properties that will store optimal networks results = [] results_header = [] #Start looping the columns; e.g., year 2000, then 2001, then 2002 for column in arange(len(data.columns.values)): current = data.columns.values[column] print("") print("Starting {0}".format(current)) #Find none blank values and assign them in list distribution purely to get the zeta values in default 'D' mode if zeta_type != 'S' and zeta_type != 'M': from NFA_zeta import zeta_default zeta_list = zeta_default( data.ix[:, column].convert_objects(convert_numeric=True).dropna()) #Define list to store all the temporarily results for the current column temp_results = [] #Compute, store, and save all networks for list of zeta coefficients for i in arange(len(zeta_list)): temp_results.append( network_calc( data.ix[:, column].convert_objects(convert_numeric=True).dropna(), zeta_list[i], column)) if record_all == 'Y': temp_zeta = [temp_results[i][1]] temp_zeta_current = int(current) save_individual_results(temp_results[i], temp_results[i][1],