def EDR(input_data):
with open(input_data, 'r') as f:
header={}
for i, row in enumerate(f.readlines()):
if i<2 or i==28:
pass
elif i<28:
header.update(header_parser(row,':')) #read the header values into a dict
elif i==29:
row=row.split()
shotnums=list(range(1,len(row)+1))
shots=['shot'+str(i) for i in shotnums]
df = pd.read_csv(input_data, sep=' ',skiprows=29,names=shots)
df=df.transpose()
#insert the header metadata as columns
for label,data in header.items():
df[label]=data
return df
def CCS(input_data):
df = pd.DataFrame.from_csv(input_data, header=14)
df.rename(columns=lambda x: x.strip(),inplace=True) #strip whitespace from column names
df=df.transpose()
cols=df.columns.tolist()
for i,x in enumerate(cols):
cols[i]=('wvl',round(float(x),5))
df.columns=pd.MultiIndex.from_tuples(cols)
#extract info from the file name
fname=os.path.basename(input_data)
df['sclock']=fname[4:13]
df['sclock']=pd.to_numeric(df['sclock'])
df['seqid']=fname[25:34].upper()
df['Pversion']=fname[34:36]
#transpose the data frame
#read the file header and put information into the dataframe as new columns
#(inefficient to store this data many times, but much easier to concatenate data from multiple files)
with open(input_data,'r') as f:
header={}
for i,row in enumerate(f.readlines()):
if i<14:
row=row.split(',')[0]
header.update(header_parser(row,'='))
for label,data in header.items():
if '_float' in label:
label=label.replace('_float','')
if label=='dark':
label='darkspec'
df[label]=data
df.index.rename('shotnum',inplace=True)
df.reset_index(level=0,inplace=True)
return df