import pylab
import voc_reader
from pylab import *
from sklearn import linear_model
from scipy import stats
from matplotlib.offsetbox import AnchoredText
# The path to where the raw files are stored
path = "../Data/wacl_data/Raw_data_files/"
f_date = '201610'
cal_file = os.listdir(path + f_date + '/MOS')
# The name of the MOS file to be analysed
Time_avg = '300S'
data_concat = mr.readin(path, f_date, cal_file, 1, 5, Time_avg)
data_voc = voc_reader.extract_voc('../Data/',
'Detailed Compound Concentrations',
'Analyte vs Time', Time_avg)
data_merge = data_concat.merge(data_voc, how='inner', on=['Time'])
sub = 'vocs6'
voc6 = ['C3H3+ (1,3-butadiene;O2+) (ppb)', 'MOS1c_Av']
VOCs6fig = plt.figure("vocs6")
ax1 = VOCs6fig.add_subplot(111)
ax2 = ax1.twinx()
colors = [
"black", "firebrick", "lightgreen", "c", "darkblue", "purple", "orange",
"forestgreen", "lightskyblue", "indigo", "dimgrey", "fuchsia"
]
ax = []
for n, c in zip(voc6, colors):
if n == 'MOS1c_Av':
except NameError:
data_concat = mean_resampled.copy(deep=True)
print(' making data_concat')
# Re-make and re-set the index to be the time column for the data_concat dataframe.
T3 = pd.datetime(2015, 1, 1, 0)
dt = pd.Series((data_concat.index - T3), index=data_concat.index, name='dt')
dt = dt.astype(int64)
data_concat = pd.concat([data_concat, dt],
axis=1,
join_axes=[data_concat.index])
stat = 'Y'
header = [
'MOS1_Av', 'MOS2_Av', 'MOS3_Av', 'MOS4_Av', 'MOS5_Av', 'MOS6_Av',
'MOS7_Av', 'MOS8_Av', 'HIH1_Av', 'LM65T1_Av', 'SV_Av'
]
#data_concat.to_csv('test.csv', index = False, columns = header)
data_concat.to_csv('test.csv', columns=header)
newindex = pd.Series(range(0, data_concat.shape[0]))
data_concat = data_concat.set_index(newindex)
# Returns the initial date and time that the file began
print(data_concat.Time[0])
print(data_concat.Time[len(data_concat.Time) - 1])
data_voc = voc_reader.extract_voc('D:/WACL/Data/',
'Detailed Compound Concentrations',
'Analyte vs Time')
#print(data_concat.Time)
data_merge = data_voc.merge(data_concat, how='inner', on=['Time'])
data_merge.to_csv('test3.csv')
import voc_reader
import MOS_reader as mr
from pylab import *
from sklearn import linear_model
from scipy import stats
# The path to where the raw files are stored
path = "../Data/wacl_data/Raw_data_files/"
f_date = '201610'
cal_file = os.listdir(path + f_date + '/MOS')
# The name of the MOS file to be analysed
data_concat = mr.readin(path, f_date, cal_file, 1, 5)
#correlation between MOSc and other signals
data_voc = voc_reader.extract_voc('..\Data\\',
'Detailed Compound Concentrations',
'Analyte vs Time')
data_merge = data_concat.merge(data_voc, how='inner', on=['Time'])
print(
np.corrcoef(data_merge['MOS1c_Av'],
data_merge['CH5O+ (methanol;H3O+) (ppb)']))
print(
np.corrcoef(data_merge['MOS1c_Av'],
data_merge['CH3CN.H+ (acetonitrile;H3O+) (ppb)']))
print(
np.corrcoef(data_merge['MOS1c_Av'],
data_merge['C3H7O+ (acetone;H3O+) (ppb)']))
print(
np.corrcoef(data_merge['MOS1c_Av'],
data_merge['C4H6O.H+ (3-buten-2-one;H3O+) (ppb)']))
print(