Helper function for processing the historical spectral and wave statistics files as well as data exported from DIWASP via write_csv in Datawell_to_DIWASP

toolbox_comparison_helper_functions.py

import pandas as pd
from datetime import datetime
from scipy.stats.stats import pearsonr

his_columns = ['date_time', 'tp', 'dirp', 'sprp', 'tz', 'hm0', 'ti', 't1', 
               'tc', 'tdw2', 'tdw1', 'tpc', 'nu','eps','qp','ss','tref','tsea',
               'bat']

hiw_columns = ['date_time','% no reception errors','hmax','tmax','h1_10',
               't1_10','h1_3','t1_3','Hav','Tav','Eps','#Waves']

def apply_date_time_index(df):
    df = df[pd.notnull(df.date_time)]
    date_times = []        
    for index,date_time_string in enumerate(df['date_time'].values):
        if type(date_time_string) == type(''):
            date_time = datetime.strptime(date_time_string[:-5],
                                          "%Y-%m-%dT%H:%M:%S")
            date_times.append(date_time)
    df.index = pd.DatetimeIndex(date_times)
    return df

def process_hist(hist_df):
    hist_df = apply_date_time_index(hist_df)
    hist_df = hist_df.drop('date_time', axis = 1)
    hist_df = hist_df.resample('30Min')
    return hist_df

def read_hist_csv_and_time_index(filepath, columns= his_columns):
    his_df = pd.read_csv(filepath, names = columns)
    return process_hist(his_df)

# Reads in csv files output from Matlab DIWASP toolbox
# and outputs timestamped Pandas Dataframes

def read_diwasp_csv(file_path, date_format="%Y-%m-%dT%Hh%MZ"):
    """Function for reading csv files created by the write_csv.m matlab file
       which output file_names, Hm0 and peak period
    """
    df = pd.read_csv(file_path)
    date_time_array = []
    for date_time_string in df['file_name'].values:
        date_time_array.append(datetime.strptime(date_time_string[-21:-4],
                                                 date_format))
        
    df.index = pd.DatetimeIndex(date_time_array)
    return df