input_output.organize

  1"""Descriptive description."""
  2
  3from copy import deepcopy
  4import csv
  5import datetime as dt
  6
  7
  8class Organize_input():
  9    def __init__(self, keys_pr, keys_fwd, keys_en=None):
 10        self.keys_pr = keys_pr
 11        self.keys_fwd = keys_fwd
 12        self.keys_en = keys_en
 13
 14    def organize(self):
 15        # Organize the data types given by DATATYPE keyword
 16        self._org_datatype()
 17        # Organize the observed data given by TRUEDATA keyword and initialize predicted data variable
 18        self._org_report()
 19
 20    def get_keys_pr(self):
 21        return deepcopy(self.keys_pr)
 22
 23    def get_keys_fwd(self):
 24        return deepcopy(self.keys_fwd)
 25
 26    def get_keys_en(self):
 27        return deepcopy(self.keys_en)
 28
 29    def _org_datatype(self):
 30        """ Check if datatype is given as a csv file. If so, we read and make a list."""
 31        if isinstance(self.keys_fwd['datatype'], str) and self.keys_fwd['datatype'].endswith('.csv'):
 32            with open(self.keys_fwd['datatype']) as csvfile:
 33                reader = csv.reader(csvfile)  # get a reader object
 34                datatype = []  # Initialize the list of csv data
 35                for rows in reader:  # Rows is a list of values in the csv file
 36                    csv_data = [None] * len(rows)
 37                    for col in range(len(rows)):
 38                        csv_data[col] = str(rows[col])
 39                    datatype.extend(csv_data)
 40            self.keys_fwd['datatype'] = datatype
 41
 42        if not isinstance(self.keys_fwd['datatype'], list):
 43            self.keys_fwd['datatype'] = [self.keys_fwd['datatype']]
 44        # make copy for problem keywords
 45        self.keys_pr['datatype'] = self.keys_fwd['datatype']
 46
 47    def _org_report(self):
 48        """
 49        Organize the input true observed data. The obs_data will be a list of length equal length of "TRUEDATAINDEX",
 50        and each entery in the list will be a dictionary with keys equal to the "DATATYPE".
 51        Also, the pred_data variable (predicted data or forward simulation) will be initialized here with the same
 52        structure as the obs_data variable.
 53
 54        .. warning:: An "N/A" entry in "TRUEDATA" is treated as a None-entry; that is, there is NOT an observed data at this
 55        assimilation step.
 56
 57        .. warning:: The array associated with the first string inputted in "TRUEDATAINDEX" is assumed to be the "main"
 58        index, that is, the length of this array will determine the length of the obs_data list! There arrays
 59        associated with the subsequent strings in "TRUEDATAINDEX" are then assumed to be a subset of the first
 60        string.
 61        An example: the first string is SOURCE (e.g., sources in CSEM), where the array will be a list of numbering
 62        for the sources; and the second string is FREQ, where the array associated will be a list of frequencies.
 63
 64        .. info:: It is assumed that the number of data associated with a subset is the same for each index in the subset.
 65        For example: If two frequencies are inputted in FREQ, then the number of data for one SOURCE index and one
 66        frequency is 1/2 of the total no. of data for that SOURCE index. If three frequencies are inputted, the number
 67        of data for one SOURCE index and one frequencies is 1/3 of the total no of data for that SOURCE index,
 68        and so on.
 69        """
 70
 71        # Extract primary indices from "TRUEDATAINDEX"
 72        if 'truedataindex' in self.keys_pr:
 73
 74            if isinstance(self.keys_pr['truedataindex'], list):  # List of prim. ind
 75                true_prim = self.keys_pr['truedataindex']
 76            else:  # Float
 77                true_prim = [self.keys_pr['truedataindex']]
 78
 79            # Check if a csv file has been included as "TRUEDATAINDEX". If so, we read it and make a list,
 80            if isinstance(self.keys_pr['truedataindex'], str) and self.keys_pr['truedataindex'].endswith('.csv'):
 81                with open(self.keys_pr['truedataindex']) as csvfile:
 82                    reader = csv.reader(csvfile)  # get a reader object
 83                    true_prim = []  # Initialize the list of csv data
 84                    for rows in reader:  # Rows is a list of values in the csv file
 85                        csv_data = [None] * len(rows)
 86                        for ind, col in enumerate(rows):
 87                            csv_data[ind] = int(col)
 88                        true_prim.extend(csv_data)
 89            self.keys_pr['truedataindex'] = true_prim
 90
 91        # Check if a csv file has been included as "REPORTPOINT". If so, we read it and make a list,
 92        if 'reportpoint' in self.keys_fwd:
 93            if isinstance(self.keys_fwd['reportpoint'], str) and self.keys_fwd['reportpoint'].endswith('.csv'):
 94                with open(self.keys_fwd['reportpoint']) as csvfile:
 95                    reader = csv.reader(csvfile)  # get a reader object
 96                    pred_prim = []  # Initialize the list of csv data
 97                    for rows in reader:  # Rows is a list of values in the csv file
 98                        csv_data = [None] * len(rows)
 99                        for ind, col in enumerate(rows):
100                            try:
101                                csv_data[ind] = int(col)
102                            except ValueError:
103                                csv_data[ind] = dt.datetime.strptime(
104                                    col, '%Y-%m-%d %H:%M:%S')
105
106                        pred_prim.extend(csv_data)
107                self.keys_fwd['reportpoint'] = pred_prim
108
109        # Check if assimindex is given as a csv file. If so, we read and make a potential 2D list (if sequential).
110        if 'assimindex' in self.keys_pr:
111            if isinstance(self.keys_pr['assimindex'], str) and self.keys_pr['assimindex'].endswith('.csv'):
112                with open(self.keys_pr['assimindex']) as csvfile:
113                    reader = csv.reader(csvfile)  # get a reader object
114                    assimindx = []  # Initialize the 2D list of csv data
115                    for rows in reader:  # Rows is a list of values in the csv file
116                        csv_data = [None] * len(rows)
117                        for col in range(len(rows)):
118                            csv_data[col] = int(rows[col])
119                        assimindx.append(csv_data)
120                self.keys_pr['assimindex'] = assimindx
121
122            # check that they are lists
123            if not isinstance(self.keys_pr['truedataindex'], list):
124                self.keys_pr['truedataindex'] = [self.keys_pr['truedataindex']]
125            if not isinstance(self.keys_fwd['reportpoint'], list):
126                self.keys_fwd['reportpoint'] = [self.keys_fwd['reportpoint']]
127            if not isinstance(self.keys_pr['assimindex'], list):
128                self.keys_pr['assimindex'] = [self.keys_pr['assimindex']]