diff --git a/docs/index.rst b/docs/index.rst
index 7c62f555cd5efd362fcc89af7dbfd38d3f81c7f0..88055f563f3dedc96009994f83ff4ce14563020f 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -37,6 +37,17 @@ Dataset
.. autoclass:: Dataset
:members:
+DataStore
+*********
+
+The .data attribute of an ``icartt.Dataset`` is a DataStore, which can be accessed to add data as follows:
+
+.. autoclass:: DataStore1001
+ :members:
+
+.. autoclass:: DataStore2110
+ :members:
+
Formats
********
diff --git a/src/icartt/__init__.py b/src/icartt/__init__.py
index 1e51075d7aef6217452489c5d52088a792d747fc..dd59964cf23e95d7b368ca6470014d9fa1406e73 100644
--- a/src/icartt/__init__.py
+++ b/src/icartt/__init__.py
@@ -17,6 +17,22 @@ del get_version
# EXPORTED TYPES
-from .dataset import Dataset, StandardNormalComments, Variable, Formats, VariableType
+from .dataset import (
+ Dataset,
+ StandardNormalComments,
+ Variable,
+ Formats,
+ VariableType,
+ DataStore1001,
+ DataStore2110,
+)
-__all__ = ("Dataset", "StandardNormalComments", "Variable", "Formats", "VariableType")
+__all__ = (
+ "Dataset",
+ "StandardNormalComments",
+ "Variable",
+ "Formats",
+ "VariableType",
+ "DataStore1001",
+ "DataStore2110",
+)
diff --git a/src/icartt/dataset.py b/src/icartt/dataset.py
index b8abad9200862379ed6c3f20ec9d462d14372a46..0e035d11cd5f8cf2e6391f7e0c6c65e9ffe04251 100644
--- a/src/icartt/dataset.py
+++ b/src/icartt/dataset.py
@@ -30,6 +30,8 @@ class VariableType(IntEnum):
class DataStore1001:
+ """Data model for FFI1001"""
+
def __init__(self, ivar, dvars):
self.ivarname = ivar.shortname
@@ -111,6 +113,8 @@ class DataStore1001:
class DataStore2110(collections.UserDict):
+ """Data model for FFI2110"""
+
def __init__(self, ivar, ibvar, auxvars, dvars):
self.ivarname = ivar.shortname
self.ibvarname = ibvar.shortname
@@ -162,6 +166,19 @@ class DataStore2110(collections.UserDict):
self.data[ivarValue] = {"AUX": auxds, "DEP": depds}
def add(self, newAuxData, newDepData):
+ """(bulk) add data, providing (structured) numpy arrays for both the auxiliary and dependent data line(s)
+ for a given ivar value.
+
+ Arrays have to have shape [ (ivar, auxvar, auxvar, ...) ] and
+ [ (ibvar, depvar, depvar, ...), ... ] for auxiliary and dependent data line(s), respectively.
+ missing values have to be set to np.nan.
+
+ :param newAuxData: auxiliary data line to be added
+ :type newAuxData: numpy.ndarray
+
+ :param newDepData: auxiliary data line(s) to be added
+ :type newDepData: numpy.ndarray
+ """
auxds = DataStore1001(self.ivar, self.auxvars)
depds = DataStore1001(self.ibvar, self.dvars)
@@ -424,7 +441,12 @@ class Dataset:
if self.defineMode:
return np.datetime64("NaT")
- if self.data.data is None or self.data.data == {}:
+ # for 1001, its an array, for 2110 a dict
+ if not isinstance(self.data.data, (np.ndarray, dict)):
+ return np.datetime64("NaT")
+
+ # it is possible to have an empty dict
+ if isinstance(self.data.data, dict) and not self.data.data:
return np.datetime64("NaT")
ref_dt = np.datetime64(datetime.datetime(*self.dateOfCollection), "ns")
diff --git a/tests/.gitignore b/tests/.gitignore
index 1bc5aa12428cefb7f40466014928b695ce8b9d71..ca7ad6b01c62341c92d143b186bdbd6d120361ab 100644
--- a/tests/.gitignore
+++ b/tests/.gitignore
@@ -1 +1 @@
-/.coverage
+/.coverage
\ No newline at end of file
diff --git a/tests/usage_examples/create_ffi1001.py b/tests/usage_examples/create_ffi1001.py
index 15602ee9b4b4f06880b9577b21d01394d38e5dbe..b544fe71f710b28016d76899adf9dd2ced2fbcc7 100644
--- a/tests/usage_examples/create_ffi1001.py
+++ b/tests/usage_examples/create_ffi1001.py
@@ -2,6 +2,9 @@ import datetime
import icartt
+# ------------------------------------------------------
+# Phase 1: define file format, properties and variables
+# ------------------------------------------------------
ict = icartt.Dataset(format=icartt.Formats.FFI1001)
@@ -48,19 +51,28 @@ ict.normalComments.freeform.append("free comment line 2")
ict.endDefineMode()
-# Add data
+# ------------------------------------------------------
+# Phase 2: after ending define mode, add data
+# ------------------------------------------------------
+
+# all data are stored as NumPy arrays, and need to be provided as such.
import numpy as np
-data = np.array([(13.4, 14.0, 2348925e5), (14.1, 14.9, 23425634e5)])
+# ivar dvar1 dvar2
+data = np.array([(15.4, 15.0, 52452495290e5)])
ict.data.add(data)
# Note 1: you are responsible to ensure that the order of elements in a data line
# corresponds to variable listing below:
print([x for x in ict.variables])
-# Note 2: for single lines, you still need to make it an array!
-data = np.array([(15.4, 15.0, 52452495290e5)])
+# Note 2: evenfor single lines, you still need to make it an array!
+
+# Note 3: multiple data lines can be added in bulk!
+# ivar dvar1 dvar2 ivar dvar1 dvar2 ...
+data = np.array([(13.4, 14.0, 2348925e5), (14.1, 14.9, 23425634e5)])
+
ict.data.add(data)
# Now, look at it in ICARTT form:
diff --git a/tests/usage_examples/create_ffi2110.py b/tests/usage_examples/create_ffi2110.py
index aee2dfbad25bb777e7f76299dd03c2c44111ec12..feadd89acf81941df98ea4144de6387df73ac4a2 100644
--- a/tests/usage_examples/create_ffi2110.py
+++ b/tests/usage_examples/create_ffi2110.py
@@ -4,6 +4,9 @@ import numpy as np
import icartt
+# ------------------------------------------------------
+# Phase 1: define file format, properties and variables
+# ------------------------------------------------------
ict = icartt.Dataset(format=icartt.Formats.FFI2110)
@@ -82,25 +85,27 @@ ict.specialComments.append("Adapt as needed.")
ict.endDefineMode()
-# Add data
-
-# for 2110, data can be added as chunks for a given ivar!
+# ------------------------------------------------------
+# Phase 2: after ending define mode, add data
+# ------------------------------------------------------
import numpy as np
+# same as for 1001, but data needs to be added in chunks for each ivar value
+
# note, the second variable ('4') is the number of dependent lines to follow
-# ivar, ndepvar, auxvar1, auxvar2, auxvar3
+# ivar, ndepvar, auxvar1, auxvar2, auxvar3
auxData = np.array([(12.3, 4, 12.5, 48.21, 10.3)])
-# ibvar, dvar1, dvar2
+# ibvar, dvar1, dvar2 ... (repeat ndepvar times)
depData = np.array(
[(0, 123, 8.4e4), (100, 122, 9.1e4), (250, 115, 9.3e4), (500, 106, 9.8e4)]
)
ict.data.add(auxData, depData)
-# ... and so forth
-auxData = np.array([(12.4, 2, 12.8, 48.41, 12.1)])
+# ... and so forth for the next chunk:
+auxData = np.array([(12.4, 2, 12.8, 48.41, 12.1)])
# ibvar, dvar1, dvar2
depData = np.array([(0, 153, 7.3e4), (270, 172, 8.9e4)])
diff --git a/tests/usage_examples/read_ffi2110.py b/tests/usage_examples/read_ffi2110.py
index 4189aaf7d035d3e56aeb7e4cabb37bd3393b547f..946a540fcc1989406dfb6902ca7a5f851b231c9b 100644
--- a/tests/usage_examples/read_ffi2110.py
+++ b/tests/usage_examples/read_ffi2110.py
@@ -11,29 +11,26 @@ ict = icartt.Dataset(
[x for x in ict.variables]
# independent, independent bounded, dependent, auxiliary variables?
-print(f"Independent variable: {ict.independentVariable.shortname}")
-print(f"Independent bounded variable: {ict.independentBoundedVariable.shortname}")
-print(f"Auxiliary variables: {', '.join([ x for x in ict.auxiliaryVariables])}")
-print(f"Dependent variables: {', '.join([ x for x in ict.dependentVariables])}")
+ict.independentVariable.shortname
+ict.independentBoundedVariable.shortname
+", ".join([x for x in ict.auxiliaryVariables])
+", ".join([x for x in ict.dependentVariables])
-# some info on a variable
-print(f"Units of variable Latitude are {ict.variables['Latitude'].units}")
-print(f"... and its missing value is {ict.variables['Latitude'].miss}")
+# some info on a variable (units, missing value of "Latitude")
+ict.variables["Latitude"].units
+ict.variables["Latitude"].miss
# get steps for which data is available:
tsteps = [x for x in ict.data]
# let's look at the first time step data
-print("First time step data:")
-print(ict.data[tsteps[0]])
+ict.data[tsteps[0]]
# auxiliary data at this time step:
-print("First time step auxiliary data:")
-print(ict.data[tsteps[0]]["AUX"][:])
+ict.data[tsteps[0]]["AUX"][:]
# dependent data at this time step:
tstepdata = ict.data[tsteps[0]]["DEP"][:]
# get the ozone mixing ratio for those data where Altitude < 10000.0:
-print(f"Ozone mixing ratio for altitudes < 10000 at time step {tsteps[0]}")
-print(tstepdata[tstepdata["Altitude[]"] < 10000.0]["O3_MR[]"])
+tstepdata[tstepdata["Altitude[]"] < 10000.0]["O3_MR[]"]