def to_dataframe(self):
""" Load Argo index and return a pandas dataframe """
# Download data: get a csv, open it as pandas dataframe, create wmo field
df = self.fs.read_csv(self.url, parse_dates=True, skiprows=[1])
# erddap date format : 2019-03-21T00:00:35Z
df['date'] = pd.to_datetime(df['date'], format="%Y-%m-%dT%H:%M:%SZ")
df['date_update'] = pd.to_datetime(df['date_update'],
format="%Y-%m-%dT%H:%M:%SZ")
df['wmo'] = df.file.apply(lambda x: int(x.split('/')[1]))
# institution & profiler mapping
institution_dictionnary = load_dict('institutions')
df['tmp1'] = df.institution.apply(
lambda x: mapp_dict(institution_dictionnary, x))
df = df.rename(columns={
"institution": "institution_code",
"tmp1": "institution"
})
profiler_dictionnary = load_dict('profilers')
df['profiler'] = df.profiler_type.apply(
lambda x: mapp_dict(profiler_dictionnary, int(x)))
df = df.rename(columns={"profiler_type": "profiler_code"})
return df
def to_dataframe(self):
""" filter local index file and return a pandas dataframe """
df = self.fs.open_dataframe(self.filter_index())
# Post-processing of the filtered index:
df['wmo'] = df['file'].apply(lambda x: int(x.split('/')[1]))
# institution & profiler mapping for all users
# todo: may be we need to separate this for standard and expert users
institution_dictionnary = load_dict('institutions')
df['tmp1'] = df.institution.apply(lambda x: mapp_dict(institution_dictionnary, x))
df = df.rename(columns={"institution": "institution_code", "tmp1": "institution"})
profiler_dictionnary = load_dict('profilers')
df['profiler'] = df.profiler_type.apply(lambda x: mapp_dict(profiler_dictionnary, int(x)))
df = df.rename(columns={"profiler_type": "profiler_code"})
return df
def to_dataframe(self):
""" filter local index file and return a pandas dataframe """
#
# Try to load cached file if requested:
if self.cache and os.path.exists(self.cachepath):
df = pd.read_csv(self.cachepath)
return df
# No cache found or requested, so we compute:
self.filter_index()
#
df = pd.read_csv(self.filtered_index)
#create datetime & wmo field
#local ftp date format 20160513065300
df['date'] = pd.to_datetime(df['date'], format="%Y%m%d%H%M%S")
df['date_update'] = pd.to_datetime(df['date_update'],
format="%Y%m%d%H%M%S")
df['wmo'] = df.file.apply(lambda x: int(x.split('/')[1]))
#
# institution & profiler mapping
try:
institution_dictionnary = load_dict('institutions')
df['tmp1'] = df.institution.apply(
lambda x: mapp_dict(institution_dictionnary, x))
profiler_dictionnary = load_dict('profilers')
df['tmp2'] = df.profiler_type.apply(
lambda x: mapp_dict(profiler_dictionnary, x))
df = df.drop(columns=['institution', 'profiler_type'])
df = df.rename(columns={
"tmp1": "institution",
"tmp2": "profiler_type"
})
except:
pass
# Possibly save in cache for later re-use
if self.cache:
df.to_csv(self.cachepath, index=False)
return df
def to_dataframe(self):
""" Load Argo index and return a pandas dataframe """
# Try to load cached file if requested:
if self.cache and os.path.exists(self.cachepath):
ds = pd.read_csv(self.cachepath)
return ds
# No cache found or requested, so we compute:
# Download data: get a csv, open it as pandas dataframe, create wmo field
df = pd.read_csv(urlopen(self.url), parse_dates=True, skiprows=[1])
# erddap date format : 2019-03-21T00:00:35Z
df['date'] = pd.to_datetime(df['date'], format="%Y-%m-%dT%H:%M:%SZ")
df['date_update'] = pd.to_datetime(df['date_update'],
format="%Y-%m-%dT%H:%M:%SZ")
df['wmo'] = df.file.apply(lambda x: int(x.split('/')[1]))
#
# institution & profiler mapping
try:
institution_dictionnary = load_dict('institutions')
df['tmp1'] = df.institution.apply(
lambda x: mapp_dict(institution_dictionnary, x))
profiler_dictionnary = load_dict('profilers')
df['tmp2'] = df.profiler_type.apply(
lambda x: mapp_dict(profiler_dictionnary, x))
df = df.drop(columns=['institution', 'profiler_type'])
df = df.rename(columns={
"tmp1": "institution",
"tmp2": "profiler_type"
})
except:
pass
# Possibly save in cache for later re-use
if self.cache:
df.to_csv(self.cachepath, index=False)
return df
def test_invalid_dictionnary_key():
d = load_dict('profilers')
assert mapp_dict(d, "invalid_key") == "Unknown"