def picarroMetCombo(filename):
met = metTrim()
sheet = pd.read_csv(filename,
encoding='utf8',
header=None,
delim_whitespace=True)
sheet.columns = ['date', 'value']
sheet['datetime'] = decToDatetime(sheet['date'].values)
sheet.drop('date', axis=1, inplace=True)
earlyVals = ~(met['datetime'] <= sheet['datetime'][0])
met.drop(earlyVals, axis=0, inplace=True)
met.reset_index(drop=True, inplace=True)
met.drop(['steady'], axis=1, inplace=True)
# merge the met data onto the concentration data by finding the nearest datetime within an hour\
sheet.dropna(axis=0, how='any', inplace=True)
picarro = pd.merge_asof(sheet.sort_values('datetime'),
met,
on='datetime',
direction='nearest',
tolerance=pd.Timedelta('1 hour'))
picarro.dropna(axis=0, how='any', inplace=True)
return picarro
def metRemove(sheet, tolerance, dropMet=True):
"""
metRemove is a function that removes values from a Summit dataset if the linked meteorlogical data is identified
as being from a polluted zone. It takes a specific dataframe as an input, and returns the same exact dataframe.
:param sheet: the dataframe can have any values but it must have a column labeled 'datetime'
:param tolerance: the integer number of hours set to link met data with
:param dropMet: default True, drops the columns of met data from the returned product. If false, met columns
remain intact
:return combo: returns the same dataframe, reindexed, polluted values removed
"""
# identify and set the tolerence
hours = f'{tolerance} hours'
timedelt = pd.Timedelta(hours)
# combine the input data with met data, dropping NaN's before and after
met = metTrim()
met.dropna(axis=0, how='any', inplace=True)
sheet.dropna(axis=0, how='any', inplace=True)
combo = pd.merge_asof(sheet.sort_values('datetime'),
met,
on='datetime',
direction='nearest',
tolerance=timedelt)
combo.dropna(axis=0, how='any', inplace=True)
# remove polluted values
speedCutoff = 1.02889 # meters/second, too slow
dirCutoff = (342, 72) # polution directions, above 342, below 72
lenOrig = len(combo)
combo = combo[combo['spd'] > speedCutoff]
combo.reset_index(drop=True, inplace=True)
valuesInRange = np.logical_or(combo['dir'] >= dirCutoff[0],
combo['dir'] <= dirCutoff[1])
combo.drop(combo[valuesInRange].index, axis=0, inplace=True)
combo.reset_index(drop=True, inplace=True)
percentChange = (1 - (len(combo) / lenOrig)) * 100
print(
f'{percentChange} percent of the data was trimmed from pollution identification'
)
# remove unnecesary steady column
badcol = ['steady']
combo.drop(badcol, axis=1, inplace=True)
if dropMet:
combo.drop(['dir', 'spd'], axis=1, inplace=True)
return combo
def metPlotQC():
register_matplotlib_converters()
# import data
met = metTrim()
timelim = (met['datetime'].iloc[0] - dt.timedelta(days=20),
met['datetime'].iloc[-1] + dt.timedelta(days=20))
speedCutoff = 1.02889 # meters/second, too slow
dirCutoff = (342, 72) # polution directions, above 342, below 72
sns.set()
f, ax = plt.subplots(ncols=2, figsize=(12, 8))
sns.despine(f)
plt.subplots_adjust(left=None,
bottom=None,
right=None,
top=None,
wspace=None,
hspace=0.5)
ax1 = sns.distplot(met['dir'], ax=ax[0])
ax1.set_title('Summit Wind Direction Histogram')
ax1.set_xlabel('Direction Clockwise from True North')
ax1.set_ylabel('Value Distribution')
# ax1.set(xlim=(timelim[0], timelim[1]))
ax2 = sns.distplot(met['spd'], ax=ax[1])
ax2.set_title('Summit Wind Speed Histogram')
ax2.set_xlabel('Wind Speed [m/s]')
ax2.set_ylabel('Value Distribution')
# ax2.set(xlim=(timelim[0], timelim[1]))
plt.show()
sns.set(style="white", font_scale=1.5)
sns.despine()
g = sns.jointplot(met['dir'],
met['spd'],
kind='hex',
cmap=cm.magma_r,
color='#e65c00')
g.set_axis_labels('Wind Direction Measured CW from True North',
'Wind Speed [m/s]',
fontsize=20)
g.fig.suptitle('Met Data from Summit, Greenland', fontsize=28)
plt.tick_params(axis='both', labelsize=18)
plt.legend()
plt.show()
def metPlot():
# import data
met = metTrim()
# wind rose plotting with just wind speed
ax = wr.WindroseAxes.from_ax()
ax.bar(met['dir'].values, met['spd'].values, normed=True, opening=0.9, edgecolor='black',
nsector=24, bins=14, cmap=cm.viridis_r, blowto=False)
ax.set_title('Wind Speed and Direction at Summit, Greenland')
ax.set_xlabel('Wind Speed in Meters per Second')
ax.set_legend()
plt.show()
return ax
def windRoseMethane():
# ---- import data
root = r'C:\Users\ARL\Desktop\J_Summit\analyses\Data'
met = metTrim()
arl = metCombo(root + r'\methane2019updated.txt')
arl.dropna(axis=0, how='any', inplace=True)
pic = pd.read_csv(root + r'\picarro_ch4.txt',
delim_whitespace=True,
encoding='utf8',
error_bad_lines=False,
header=None)
flask = pd.read_csv(root + r'\flask_ch4.txt',
delim_whitespace=True,
error_bad_lines=False,
header=None)
# ---- combining datasets (met and picarro)
pic.columns = ['date', 'value']
pic['datetime'] = decToDatetime(pic['date'].values)
pic.drop('date', axis=1, inplace=True)
met.drop(['steady'], axis=1, inplace=True)
# merge the met data onto the concentration data by finding the nearest datetime within an hour
pic.dropna(axis=0, how='any', inplace=True)
picarro = pd.merge_asof(pic.sort_values('datetime'),
met,
on='datetime',
direction='nearest',
tolerance=pd.Timedelta('1 hour'))
picarro.dropna(axis=0, how='any', inplace=True)
# ---- combining datasets (flask and met)
met = metTrim()
colnames = ['yr', 'mo', 'dy', 'hr', 'val']
flask.columns = colnames
flask['datetime'] = createDatetime(flask['yr'], flask['mo'], flask['dy'],
flask['hr'])
flask.drop(['yr', 'mo', 'dy', 'hr'], axis=1, inplace=True)
earlyVals = (met['datetime'] <= flask['datetime'][0])
met.drop(['steady'], axis=1, inplace=True)
# merge the met data onto the concentration data by finding the nearest datetime within an hour
flaskMet = pd.merge_asof(flask,
met,
on='datetime',
direction='nearest',
tolerance=pd.Timedelta('1 hour'))
flaskMet.dropna(axis=0, how='any', inplace=True)
# ---- plotting
fig, (ax1, ax2, ax3) = plt.subplots(1,
3,
subplot_kw=dict(projection='windrose'))
fig.suptitle('Methane Conc. at Summit by Wind Direction', fontsize=16)
plt.subplots_adjust(left=None,
bottom=None,
right=None,
top=None,
wspace=0.2,
hspace=-0.3)
# setup GC methane windrose
ax1.bar(arl['dir'].values,
arl['val'].values,
normed=False,
opening=0.9,
edgecolor='black',
nsector=24,
bins=14,
cmap=cm.viridis_r,
blowto=False)
ax1.set_title('GCFID Methane Conc. [ppb]\n')
ax1.set_legend(loc=8,
fancybox=True,
shadow=True,
bbox_to_anchor=(0.5, -1.05))
# setup picarro methane windrose
ax2.bar(picarro['dir'].values,
picarro['value'].values,
normed=False,
opening=0.9,
edgecolor='black',
nsector=24,
bins=14,
cmap=cm.viridis_r,
blowto=False)
ax2.set_title('Picarro Methane Conc. [ppb]\n', )
ax2.set_legend(loc=8,
fancybox=True,
shadow=True,
bbox_to_anchor=(0.5, -1.05))
# setup flask methane windrose
ax3.bar(flaskMet['dir'].values,
flaskMet['val'].values,
normed=False,
opening=0.9,
edgecolor='black',
nsector=24,
bins=14,
cmap=cm.viridis_r,
blowto=False)
ax3.set_title('Flask Methane Conc. [ppb]\n')
ax3.set_legend(loc=8,
fancybox=True,
shadow=True,
bbox_to_anchor=(0.5, -1.05))
plt.show()