def parse_kmer_file(filename, kmer_col, weight_col, header=True, sep='\t'):
"""Parse a columnar file to build trinucleotide matrix.
import bz2 as _bz2
import gzip as _gzip
Parameters
----------
filename : str
Path to the file to parse
kmer_col : int
0-based integer column number for the kmer column
weight_col : int
0-based integer column number for the weight column
header : bool
If True, ignore first line
sep : str
Column to split the file on
Returns
-------
trinucleotide_weights : dict
{trinucleotide1: {trinucleotide2: weight_change}}
weight_change is trinucleotide2-trinucleotide1, or what the weight
change would be if going from trinucleotide2 to trinucleotide1
"""
kmers = []
with _open_zipped(filename) as fin:
if header:
fin.readline()
for l in fin:
f = l.strip().split(sep)
kmers.append((f[kmer_col], flt(f[weight_col])))
return _scan.get_weights(kmers)
sys.argv = filter(None, sys.argv)
if len(sys.argv) < 2:
print "USE: re_config.py CONF DIR_CONF"
sys.exit(0)
conf1 = sys.argv[1]
dir_cnf = sys.argv[2]
root_dir = sycallo("echo $FIT3DP_PATH") + "/.."
#print root_dir
root_dirn = root_dir.replace(" ", "\ ")
f1 = open(dir_cnf + "/" + conf1, "r")
f1a = open(dir_cnf + "/" + conf1 + "_n", "w")
#print dir_cnf+"/"+conf1+"_n"
cont = 0
for line in f1:
cont = cont + 1
if cont == 4:
val = flt(line.replace("\n", ""))
if cont >= 5 and cont <= 5 + val - 1:
data = line.replace("\n", "").split(" ")
data = filter(None, data)
#print line.replace("\n","")
dir1 = root_dir + "/" + data[3]
dir2 = root_dir + "/" + data[5]
f1a.write(data[0] + " " + data[1] + " " + data[2] + " " + dir1 + " " +
data[4] + " " + dir2 + " " + data[6] + " " + data[7] + "\n")
else:
f1a.write(line)
f1a.close()
def sycall(comand):
import os
linp=comand
print linp+" | PROCESSING"
flog.write(linp+"\n")
os.system(comand)
print "DONE"
sys.argv=filter(None,sys.argv)
if len(sys.argv) < 1:
print "USE: ana_dingle.py NAME"
sys.exit(0)
n_proc=5
vel_light=flt(299792.458)
plot=2
plot_rss=0
VER="v1_3_2"
VER="MPL-5"
DIR_DATA="/Users/hjibarram/Dropbox/MaNGA_python/ana_single/disk-d/sanchez/ppak/legacy/DATA/SSP/MaNGA_lin"
DIR_DATA_OUT="/Users/hjibarram/Dropbox/MaNGA_python/ana_single/disk-b/manga/data/"+VER+"/MaNGA_lin_ana"
DIR_PLOTS="/Users/hjibarram/Dropbox/MaNGA_python/ana_single/home/manga/MaNGA_figs"
max_size=10
frac=0.9
#template="home/sanchez/ppak/legacy/gsd61_156.fits"
#temp_2="disk-b/sanchez/ppak/legacy/miles_2.fits"
#temp_3="home/sanchez/ppak/legacy/gsd61_12.fits"
#temp_4="disk-b/sanchez/ppak/legacy/miles_2_gas.fits"
#temp_5="disk-b/sanchez/ppak/legacy/templates/ssp_lib.4.fits"
def parse_pidata(pifile):
" parse raspberrypi data file from JHO"
df = pd.read_csv(pifile, delimiter=";")
for i, d in enumerate(df[df.columns[2]]):
if "[" in d:
istart = i
break
data = []
tmelar = []
tme = flt(0.0)
for d, t in zip(df.iloc[istart:, 2], df.iloc[istart:, 0]):
tmel = tme
tme += flt(0.2)
tme = np.round(tme, 1)
if isinstance(d, float) and np.isnan(d):
continue
if "*" in d or "#" in d or "L" in d:
tme -= flt(0.2)
tme = np.round(tme, 1)
continue
if "start" in d or "Connect" in d:
continue
st = d.replace("[", "").replace("]", "").split(",")
nums = []
for s in st:
if "None" not in s:
nums.append(float(s))
else:
nums.append(np.nan)
if any(nums) == 0.0:
continue
dt = datetime.strptime(t, "%Y-%m-%d %H:%M:%S")
deltat = (dt - data[0][-1]).total_seconds() if data else 0.0
if int(tmel) != int(deltat):
tme = deltat
data.append(nums + [tmel, dt])
data = np.array(data)
fs2kts = 0.592484
ft2m = 0.3048
ddict = {
"altitude": {
"units": "ft",
"values": ay(-data[:, 0], dtype=flt)
},
"heading": {
"units": "radians",
"values": ay(data[:, 1], dtype=flt)
},
"speed": {
"units": "kts",
"values": ay(data[:, 2] * fs2kts, dtype=flt)
},
"pitch": {
"units": "radians",
"values": ay(data[:, 3], dtype=flt)
},
"roll": {
"units": "radians",
"values": ay(data[:, 4], dtype=flt)
},
"pressure": {
"units": "bar",
"values": ay(data[:, 5], dtype=flt)
},
"rpm": {
"units": "RPM",
"values": ay(data[:, 6], dtype=flt)
},
"ecuvoltage": {
"units": "V",
"values": ay(data[:, 7], dtype=flt)
},
"cht1": {
"units": "C",
"values": ay(data[:, 8], dtype=flt)
},
"cht2": {
"units": "C",
"values": ay(data[:, 9], dtype=flt)
},
"fuelflow": {
"units": "ml/min",
"values": ay(data[:, 10], dtype=flt)
},
"totalfuel": {
"units": "ml",
"values": ay(data[:, 11], dtype=flt)
},
"gpse": {
"units": "degrees",
"values": ay(data[:, 12], dtype=flt)
},
"gpsn": {
"units": "degrees",
"values": ay(data[:, 13], dtype=flt)
},
"voltage": {
"units": "V",
"values": ay(data[:, 14], dtype=flt)
},
"servovolt": {
"units": "V",
"values": ay(data[:, 15], dtype=flt)
},
"fuelpresence": {
"units": "-",
"values": ay(data[:, 16], dtype=flt)
},
"payloadtemp": {
"units": "C",
"values": ay(data[:, 17], dtype=flt)
},
"mptemp": {
"units": "C",
"values": ay(data[:, 18], dtype=flt)
},
"zaccel": {
"units": "m/s^2",
"values": ay(data[:, 19] * ft2m, dtype=flt)
},
"xaccel": {
"units": "m/s^2",
"values": ay(data[:, 20] * ft2m, dtype=flt)
},
"yaccel": {
"units": "m/s^2",
"values": ay(data[:, 21] * ft2m, dtype=flt)
},
"timeelapsed": {
"units": "sec",
"values": ay(data[:, 22], dtype=flt)
},
"time": {
"units": "-",
"values": data[:, 23]
}
}
return ddict