def set_parameter_values(watertxt_data, name, values):
"""
Set new values for a particular parameter contained in the watertxt_data
dictionary.
Parameters
----------
watertxt_data : dictionary
Dictionary holding data found in WATER output text file.
name : string
String name of parameter
values : numpy array
Array of data values
Returns
-------
watertxt_data : dictionary
Dictionary holding updated data values
"""
for parameter in watertxt_data['parameters']:
if parameter["name"].split('(')[0].strip() == name.split("(")[0].strip():
param_mean, param_max, param_min = helpers.compute_simple_stats(data = values)
parameter["data"] = values
parameter["mean"] = param_mean
parameter["max"] = param_max
parameter["min"] = param_min
return watertxt_data
def set_parameter_values(watertxt_data, name, values):
"""
Set new values for a particular parameter contained in the watertxt_data
dictionary.
Parameters
----------
watertxt_data : dictionary
Dictionary holding data found in WATER output text file.
name : string
String name of parameter
values : numpy array
Array of data values
Returns
-------
watertxt_data : dictionary
Dictionary holding updated data values
"""
for parameter in watertxt_data['parameters']:
if parameter["name"].split('(')[0].strip() == name.split(
"(")[0].strip():
param_mean, param_max, param_min = helpers.compute_simple_stats(
data=values)
parameter["data"] = values
parameter["mean"] = param_mean
parameter["max"] = param_max
parameter["min"] = param_min
return watertxt_data
def add_parameter(watertxt_data, name, param_data):
"""
Add a parameter to the list of existing parameters in watertxt_data and the
list of column names. The new parameter will is appended to the end of the
existing parameter list.
Parameters
----------
watertxt_data : dictionary
Dictionary holding data found in WATER output text file.
name : string
String name of parameter
param_data : numpy array
Array of parameter data values
Returns
-------
watertxt_data : dictionary
Updated dictionary with the new parameter added.
"""
# add name to column names
watertxt_data["column_names"].append(name)
# compute simple stats
param_mean, param_max, param_min = helpers.compute_simple_stats(
data=param_data)
# find last index
indices = []
for parameter in watertxt_data["parameters"]:
indices.append(parameter["index"])
# add to parameter list
watertxt_data["parameters"].append({
"name": name,
"index": max(indices) + 1,
"data": param_data,
"mean": param_mean,
"max": param_max,
"min": param_min
})
return watertxt_data
def add_parameter(watertxt_data, name, param_data):
"""
Add a parameter to the list of existing parameters in watertxt_data and the
list of column names. The new parameter will is appended to the end of the
existing parameter list.
Parameters
----------
watertxt_data : dictionary
Dictionary holding data found in WATER output text file.
name : string
String name of parameter
param_data : numpy array
Array of parameter data values
Returns
-------
watertxt_data : dictionary
Updated dictionary with the new parameter added.
"""
# add name to column names
watertxt_data["column_names"].append(name)
# compute simple stats
param_mean, param_max, param_min = helpers.compute_simple_stats(data = param_data)
# find last index
indices = []
for parameter in watertxt_data["parameters"]:
indices.append(parameter["index"])
# add to parameter list
watertxt_data["parameters"].append({"name": name, "index": max(indices) + 1, "data": param_data,
"mean": param_mean, "max": param_max, "min": param_min}
)
return watertxt_data
def read_file_in(filestream):
"""
Read and process a WATER \*.txt file. Finds any parameter and its respective data.
Parameters
----------
filestream : file object
A python file object that contains an open data file.
Returns
-------
data : dictionary
Returns a dictionary containing data found in data file.
Notes
-----
data = {
"user": None,
"date_created": None,
"stationid": None,
"column_names": None,
"dates": [],
"parameters": [],
}
The "parameters" key contains a list of dictionaries containing
the parameters found in the data file
See Also
--------
create_parameter : Create new dictionary to hold parameter data
"""
# read all the lines in the filestream
data_file = filestream.readlines()
# regular expression patterns in data file
patterns = {
"user": "******",
"date_created": "(Date:)\t(.+)",
"stationid": "(StationID:)\t(.+)",
"column_names": "(Date)\t(.+)",
"data_row": "([0-9]{1,2}/[0-9]{1,2}/[0-9]{4})\t(.+)"
}
# initialize a dictionary to hold all the data of interest
data = {
"user": None,
"date_created": None,
"stationid": None,
"column_names": None,
"dates": [],
"parameters": []
}
# process file
for line in data_file:
# find match
match_user = re.search(pattern = patterns["user"], string = line)
match_date_created = re.search(pattern = patterns["date_created"], string = line)
match_stationid = re.search(pattern = patterns["stationid"], string = line)
match_column_names = re.search(pattern = patterns["column_names"], string = line)
match_data_row = re.search(pattern = patterns["data_row"], string = line)
# if match is found, add it to data dictionary
if match_user:
data["user"] = match_user.group(2)
if match_date_created:
data["date_created"] = match_date_created.group(2)
if match_stationid:
data["stationid"] = match_stationid.group(2)
if match_column_names:
data["column_names"] = match_column_names.group(2).split("\t")
# create a dictionary for each column_name (excluding "Date")
for name in data["column_names"]:
parameter = create_parameter(name = name, index = data["column_names"].index(name), data = [], mean = None, max = None, min = None)
data["parameters"].append(parameter)
if match_data_row:
# add date to data dictionary
date = get_date(date_str = match_data_row.group(1))
data["dates"].append(date)
for parameter in data["parameters"]:
value = match_data_row.group(2).split("\t")[parameter["index"]]
value = helpers.convert_to_float(value = value, helper_str = "parameter {} on {}".format(parameter["name"], date.strftime("%Y-%m-%d_%H.%M")))
parameter["data"].append(float(value))
# convert the date list to a numpy array
data["dates"] = np.array(data["dates"])
# convert each parameter data list in data["parameter"] convert to a numpy array and
# compute mean, max, and min
for parameter in data["parameters"]:
parameter["data"] = np.array(parameter["data"])
param_mean, param_max, param_min = helpers.compute_simple_stats(data = parameter["data"])
parameter["mean"] = param_mean
parameter["max"] = param_max
parameter["min"] = param_min
# return data
return data
def read_file_in(filestream):
"""
Read and process a WATER \*.txt file. Finds any parameter and its respective data.
Parameters
----------
filestream : file object
A python file object that contains an open data file.
Returns
-------
data : dictionary
Returns a dictionary containing data found in data file.
Notes
-----
data = {
"user": None,
"date_created": None,
"stationid": None,
"column_names": None,
"dates": [],
"parameters": [],
}
The "parameters" key contains a list of dictionaries containing
the parameters found in the data file
See Also
--------
create_parameter : Create new dictionary to hold parameter data
"""
# read all the lines in the filestream
data_file = filestream.readlines()
# regular expression patterns in data file
patterns = {
"user": "******",
"date_created": "(Date:)\t(.+)",
"stationid": "(StationID:)\t(.+)",
"column_names": "(Date)\t(.+)",
"data_row": "([0-9]{1,2}/[0-9]{1,2}/[0-9]{4})\t(.+)"
}
# initialize a dictionary to hold all the data of interest
data = {
"user": None,
"date_created": None,
"stationid": None,
"column_names": None,
"dates": [],
"parameters": []
}
# process file
for line in data_file:
# find match
match_user = re.search(pattern=patterns["user"], string=line)
match_date_created = re.search(pattern=patterns["date_created"],
string=line)
match_stationid = re.search(pattern=patterns["stationid"], string=line)
match_column_names = re.search(pattern=patterns["column_names"],
string=line)
match_data_row = re.search(pattern=patterns["data_row"], string=line)
# if match is found, add it to data dictionary
if match_user:
data["user"] = match_user.group(2)
if match_date_created:
data["date_created"] = match_date_created.group(2)
if match_stationid:
data["stationid"] = match_stationid.group(2)
if match_column_names:
data["column_names"] = match_column_names.group(2).split("\t")
# create a dictionary for each column_name (excluding "Date")
for name in data["column_names"]:
parameter = create_parameter(
name=name,
index=data["column_names"].index(name),
data=[],
mean=None,
max=None,
min=None)
data["parameters"].append(parameter)
if match_data_row:
# add date to data dictionary
date = get_date(date_str=match_data_row.group(1))
data["dates"].append(date)
for parameter in data["parameters"]:
value = match_data_row.group(2).split("\t")[parameter["index"]]
value = helpers.convert_to_float(
value=value,
helper_str="parameter {} on {}".format(
parameter["name"], date.strftime("%Y-%m-%d_%H.%M")))
parameter["data"].append(float(value))
# convert the date list to a numpy array
data["dates"] = np.array(data["dates"])
# convert each parameter data list in data["parameter"] convert to a numpy array and
# compute mean, max, and min
for parameter in data["parameters"]:
parameter["data"] = np.array(parameter["data"])
param_mean, param_max, param_min = helpers.compute_simple_stats(
data=parameter["data"])
parameter["mean"] = param_mean
parameter["max"] = param_max
parameter["min"] = param_min
# return data
return data
