getting rid of print() statements

msnoise/api.py

@@ -556,17 +556,17 @@ def check_stations_uniqueness(session, station):
     if station.count(".") == 2:
         return station
 
-    print("It seems you're voluntarily missing the location code for"
-          " \"%s\". We'll handle this automatically, if there are no "
-          "conflicts." % station)
+    logging.info("It seems you're voluntarily missing the location code for"
+                 " \"%s\". We'll handle this automatically, if there are no "
+                 "conflicts." % station)
     net, sta = station.split(".")
     locs = get_station(session, net, sta).locs()
     if len(locs) != 1:
-        print("There are more than 1 location codes for this station: "
-              "%s" % locs)
+        logging.info("There are more than 1 location codes for this station: "
+                     "%s" % locs)
         return station
     station += ".%s" % locs[0]
-    print("Found %s to be the unique solution for this station" % station)
+    logging.info("Found %s to be the unique solution for this station" % station)
     return station
 
 
@@ -920,7 +920,7 @@ def get_next_job(session, flag='T', jobtype='CC', limit=99999):
                    filter(Job.jobtype == jobtype).
                    filter(Job.flag == flag).first().day).\
             limit(limit).with_for_update()
-        # print(jobs.statement.compile(compile_kwargs={"literal_binds": True}))
+
         tmp = jobs.all()
         refs = [_.ref for _ in tmp]
         q = update(Job).values({"flag":"I"}).where(Job.ref.in_(refs))
@@ -937,7 +937,7 @@ def get_dvv_jobs(session, flag='T', jobtype='DVV', limit=99999):
         jobs = session.query(Job).filter(Job.jobtype == jobtype). \
             filter(Job.flag == flag). \
             limit(limit).with_for_update()
-        # print(jobs.statement.compile(compile_kwargs={"literal_binds": True}))
+
         tmp = jobs.all()
         refs = [_.ref for _ in tmp]
         q = update(Job).values({"flag": "I"}).where(Job.ref.in_(refs))
@@ -1448,7 +1448,7 @@ def get_results(session, station1, station2, filterid, components, dates,
     base = os.path.join("STACKS", "%02i" % filterid,
                         "%03i_DAYS" % mov_stack, components,
                         "%s_%s" % (station1, station2), "%s") + extension
-    print("Reading files... in %s" % base)
+    logging.debug("Reading files... in %s" % base)
     lastday = dates[0]
     for j, date in enumerate(dates):
         daystack = base % str(date)
@@ -2026,7 +2026,7 @@ def psd_read_results(net, sta, loc, chan, datelist, format='PPSD', use_cache=Tru
     import tempfile
     fn = os.path.join(tempfile.gettempdir(), "MSNOISE-PSD", fn)
     if use_cache and os.path.isfile(fn):
-        print("I found this cool file: %s" % fn)
+        logging.debug("I found this cool file: %s" % fn)
         ppsd = PPSD.load_npz(fn)
     else:
         first = True
@@ -2038,7 +2038,7 @@ def psd_read_results(net, sta, loc, chan, datelist, format='PPSD', use_cache=Tru
                                   net, sta, loc, chan, day.year, jday))
             files = glob.glob(toglob)
             if not len(files):
-                print("No files found for %s.%s.%s.%s: %s" % (
+                logging.error("No files found for %s.%s.%s.%s: %s" % (
                 net, sta, loc, chan, day))
                 continue
             file = files[0]
@@ -2132,15 +2132,13 @@ def xr_create_or_open(fn, taxis=[], name="CCF"):
         dr = xr.DataArray(data, coords=[times, level0, level1],
                           dims=["times", "level0", "level1"])
     else:
-        print("Not implemented, name=%s invalid." % name)
+        logging.error("Not implemented, name=%s invalid." % name)
         sys.exit(1)
     dr.name = name
     return dr.to_dataset()
 
 
 def xr_insert_or_update(dataset, new):
-    print("dataset", type(dataset))
-    print("new", type(new))
     tt = new.merge(dataset, compat='override', combine_attrs="drop_conflicts")
     return tt.combine_first(dataset)
 
@@ -2167,15 +2165,16 @@ def xr_save_ccf(station1, station2, components, filterid, mov_stack, taxis, new,
         xr_save_and_close(dr, fullpath)
         return dr
 
+
 def xr_get_ccf(station1, station2, components, filterid, mov_stack, taxis):
     path = os.path.join("STACKS2", "%02i" % filterid,
                         "%03i_DAYS" % mov_stack, "%s" % components)
     fn = "%s_%s.nc" % (station1, station2)
 
     fullpath = os.path.join(path, fn)
     if not os.path.isfile(fullpath):
-        print("FILE DOES NOT EXIST: %s, skipping" % fullpath)
-        raise FileNotFoundError
+        # logging.error("FILE DOES NOT EXIST: %s, skipping" % fullpath)
+        raise FileNotFoundError(fullpath)
     data = xr_create_or_open(fullpath, taxis, name="CCF")
     return data.CCF.to_dataframe().unstack().droplevel(0, axis=1)
 
@@ -2201,8 +2200,8 @@ def xr_get_ref(station1, station2, components, filterid, taxis):
 
     fullpath = os.path.join(path, fn)
     if not os.path.isfile(fullpath):
-        print("FILE DOES NOT EXIST: %s, skipping" % fullpath)
-        raise FileNotFoundError
+        # logging.error("FILE DOES NOT EXIST: %s, skipping" % fullpath)
+        raise FileNotFoundError(fullpath)
     data = xr_create_or_open(fullpath, taxis, name="REF")
     return data.CCF.to_dataframe()
 
@@ -2232,8 +2231,8 @@ def xr_get_mwcs(station1, station2, components, filterid, mov_stack):
                       "%s" % components,
                       "%s_%s.nc" % (station1, station2))
     if not os.path.isfile(fn):
-        print("FILE DOES NOT EXIST: %s, skipping" % fn)
-        raise FileNotFoundError
+        # logging.error("FILE DOES NOT EXIST: %s, skipping" % fn)
+        raise FileNotFoundError(fn)
     data = xr_create_or_open(fn, name="MWCS")
     data = data.MWCS.to_dataframe().reorder_levels(['times', 'taxis', 'keys']).unstack().droplevel(0, axis=1).unstack()
     return data
@@ -2247,8 +2246,6 @@ def xr_save_dtt(station1, station2, components, filterid, mov_stack, dataframe):
     if not os.path.isdir(os.path.split(fn)[0]):
         os.makedirs(os.path.split(fn)[0])
     d = dataframe.stack()
-    print("OUTPUT:")
-    print(d.head())
     d.index = d.index.set_names(["times", "keys"])
     d.columns = ["DTT"]
     dr = xr_create_or_open(fn, taxis=[], name="DTT")
@@ -2263,8 +2260,8 @@ def xr_get_dtt(station1, station2, components, filterid, mov_stack):
                       "%s" % components,
                       "%s_%s.nc" % (station1, station2))
     if not os.path.isfile(fn):
-        print("FILE DOES NOT EXIST: %s, skipping" % fn)
-        raise FileNotFoundError
+        # logging.error("FILE DOES NOT EXIST: %s, skipping" % fn)
+        raise FileNotFoundError(fn)
     dr = xr_create_or_open(fn, taxis=[], name="DTT")
     data = dr.DTT.to_dataframe().reorder_levels(['times', 'keys']).unstack().droplevel(0, axis=1)
     return data
@@ -2293,8 +2290,8 @@ def xr_get_dvv(components, filterid, mov_stack):
                       "%03i_DAYS" % mov_stack,
                       "%s.nc" % components)
     if not os.path.isfile(fn):
-        print("FILE DOES NOT EXIST: %s, skipping" % fn)
-        raise FileNotFoundError
+        # logging.error("FILE DOES NOT EXIST: %s, skipping" % fn)
+        raise FileNotFoundError(fn)
     data = xr_create_or_open(fn, name="DVV")
     data = data.DVV.to_dataframe().reorder_levels(['times', 'level1', 'level0']).unstack().droplevel(0, axis=1).unstack()
     return data

msnoise/msnoise_admin.py

@@ -478,7 +478,6 @@ def index(self):
         params = get_params(db)
         station1, station2 = pairs[pair]['text'].replace('.', '_').split(' - ')
         start, end, dates = build_movstack_datelist(db)
-        print(station1, station2, filter, component, dates, format)
         i, result = get_results(db,station1, station2, filter, component, dates,
                                 format=format, params=params)
 
@@ -649,7 +648,6 @@ def dataAvail():
     db = connect()
     data = get_data_availability(db, net=data['net'], sta=data['sta'],
                                  loc=data['loc'], chan='HHZ')
-    print(data)
     o = {'dates': [o.starttime.strftime('%Y-%m-%d') for o in data]}
     db.close()
     o['result'] = 'ok'
@@ -751,7 +749,6 @@ def PSDAvail():
     data = flask.request.get_json()
     if not data:
         data = flask.request.args
-    print(data)
     fn = os.path.join(os.getcwd(), "PSD", "PNG", "*", data["net"], data["sta"], "%s.D"%data["chan"], "*")
     files = sorted(glob.glob(fn))
     o = {}
@@ -783,7 +780,6 @@ def PSD_PNG():
         year = "%04i"%d.year
     fn = os.path.join(os.getcwd(), "PSD", "PNG", year, data["net"], data["sta"],
                       "%s.D" % data["chan"], file)
-    print(fn)
     format = "png"
     if 'format' in data:
         format = data["format"]

msnoise/plots/ccftime.py

@@ -47,7 +47,9 @@
 
 def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, seismic=False,
          show=False, outfile=None, envelope=False, refilter=None,
-         normalize=None, **kwargs):
+         normalize=None, loglevel="INFO", **kwargs):
+    logger = get_logger('msnoise.cc_plot_ccftime', loglevel,
+                        with_pid=True)
     db = connect()
     maxlag = float(get_config(db, 'maxlag'))
     samples = get_maxlag_samples(db)
@@ -66,23 +68,23 @@ def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, seismic=False,
         freqmax = float(freqmax)
 
     if sta2 < sta1:
-        print("Stations STA1 STA2 should be sorted alphabetically")
+        logger.error("Stations STA1 STA2 should be sorted alphabetically")
         return
 
     sta1 = check_stations_uniqueness(db, sta1)
     sta2 = check_stations_uniqueness(db, sta2)
 
     pair = "%s:%s" % (sta1, sta2)
 
-    print("Fetching CCF data for %s-%s-%i-%i" % (pair, components, filterid,
+    logger.info("Fetching CCF data for %s-%s-%i-%i" % (pair, components, filterid,
                                                  mov_stack))
     stack_total = xr_get_ccf(sta1, sta2, components, filterid, mov_stack, taxis)
 
     # convert index to mdates
     stack_total.index = mdates.date2num(stack_total.index.to_pydatetime())
 
     if len(stack_total) == 0:
-        print("No CCF found for this request")
+        logger.error("No CCF found for this request")
         return
 
     if normalize == "common":
@@ -137,7 +139,7 @@ def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, seismic=False,
                                                               filterid,
                                                               mov_stack))
         outfile = "ccftime " + outfile
-        print("output to:", outfile)
+        logger.info("output to:", outfile)
         plt.savefig(outfile)
     if show:
         plt.show()

msnoise/plots/distance.py

@@ -22,6 +22,8 @@
 
 def main(filterid, components, ampli=1, show=True, outfile=None,
          refilter=None, virtual_source=None, **kwargs):
+    logger = get_logger('msnoise.plotdistance_child', "DEBUG",
+                        with_pid=True)
     db = connect()
 
     pairs = get_station_pairs(db, used=1)
@@ -61,7 +63,8 @@ def main(filterid, components, ampli=1, show=True, outfile=None,
                     ref = xr_get_ref(sta1, sta2, components, filterid, taxis)
                     ref = Trace(data=ref.CCF.values)
                     ref.stats.sampling_rate = cc_sampling_rate
-                except FileNotFoundError:
+                except FileNotFoundError as fullpath:
+                    logger.error("FILE DOES NOT EXIST: %s, skipping" % fullpath)
                     continue
 
                 if refilter:

msnoise/plots/spectime.py

@@ -45,12 +45,14 @@
 
 from msnoise.api import build_movstack_datelist, connect, get_config, \
     get_filters, get_results, check_stations_uniqueness, xr_get_ccf,\
-    get_t_axis
+    get_t_axis, get_logger
 
 
 def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, show=False,
-         outfile=False, refilter=None, startdate=None, enddate=None, **kwargs):
-
+         outfile=False, refilter=None, startdate=None, enddate=None,
+         loglevel="INFO", **kwargs):
+    logger = get_logger('msnoise.cc_plot_spectime', loglevel,
+                        with_pid=True)
     db = connect()
     cc_sampling_rate = float(get_config(db, 'cc_sampling_rate'))
     start, end, datelist = build_movstack_datelist(db)
@@ -66,23 +68,23 @@ def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, show=False,
         freqmax = float(freqmax)
 
     if sta2 < sta1:
-        print("Stations STA1 STA2 should be sorted alphabetically")
+        logger.error("Stations STA1 STA2 should be sorted alphabetically")
         return
 
     sta1 = check_stations_uniqueness(db, sta1)
     sta2 = check_stations_uniqueness(db, sta2)
 
     pair = "%s:%s" % (sta1, sta2)
 
-    print("New Data for %s-%s-%i-%i" % (pair, components, filterid,
+    logger.info("Fetching CCF data for %s-%s-%i-%i" % (pair, components, filterid,
                                         mov_stack))
     stack_total = xr_get_ccf(sta1, sta2, components, filterid, mov_stack, taxis)
 
     # convert index to mdates
     stack_total.index = mdates.date2num(stack_total.index.to_pydatetime())
 
     if len(stack_total) == 0:
-        print("No CCF found for this request")
+        logger.error("No CCF found for this request")
         return
     ax = plt.subplot(111)
     for i, line in stack_total.iterrows():
@@ -122,7 +124,6 @@ def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, show=False,
     ax.set_title(title)
 
     cursor = Cursor(ax, useblit=True, color='red', linewidth=1.2)
-    print(outfile)
     if outfile:
         if outfile.startswith("?"):
             pair = pair.replace(':', '-')
@@ -131,7 +132,7 @@ def main(sta1, sta2, filterid, components, mov_stack=1, ampli=5, show=False,
                                                               filterid,
                                                               mov_stack))
         outfile = "spectime " + outfile
-        print("output to:", outfile)
+        logger.info("output to:", outfile)
         plt.savefig(outfile)
     if show:
         plt.show()

msnoise/ppsd_compute.py

@@ -111,14 +111,14 @@ def main(loglevel="INFO", njobs_per_worker=9999):
             continue
         for job in jobs:
             net, sta, loc = job.pair.split('.')
-            print("Processing %s"% job.pair)
+            logger.debug("Processing %s"% job.pair)
             gd = UTCDateTime(job.day).datetime
             files = get_data_availability(
                 db, net=net, sta=sta, loc=loc,
                 starttime=(UTCDateTime(job.day) - 1.5 * ppsd_length).datetime,
                 endtime=gd)
             if len(files) == 0:
-                print("No files found for %s" % job.day)
+                logger.error("No files found for %s" % job.day)
                 continue
 
             for comp in ppsd_components:

msnoise/preprocessing.py

@@ -107,7 +107,7 @@ def preprocess(db, stations, comps, goal_day, params, responses=None):
                 datafiles[station][file.chan[-1]].append(fullpath)
             else:
                 MULTIPLEX = True
-                print("Mutliplex mode, reading the files")
+                logger.debug("Mutliplex mode, reading the files")
                 fullpath = os.path.join(file.path, file.file)
                 multiplexed = sorted(glob.glob(fullpath))
                 for comp in comps:

msnoise/psd_compute_rms.py

@@ -85,7 +85,7 @@ def main(loglevel="INFO", njobs_per_worker=9999):
         for job in jobs:
             net, sta, loc = job.pair.split('.')
             if station is None:
-                print("Processing %s" % (job.pair))
+                logger.debug("Processing %s" % (job.pair))
                 station = get_station(db, net, sta)
             for chan in station.chans():
                 if chan not in datelists:
@@ -96,13 +96,13 @@ def main(loglevel="INFO", njobs_per_worker=9999):
             if not len(datelists[chan]):
                 continue
             seed_id = "%s.%s.%s.%s" % (net, sta, loc, chan)
-            print("Will open HDFstore: %s" % seed_id)
+            logger.debug("Will open HDFstore: %s" % seed_id)
             store = hdf_open_store(seed_id, mode="r")
 
             s = datelists[chan][0].strftime("%Y-%m-%d %H:%M:%S")
             e = (datelists[chan][-1] + datetime.timedelta(days=1)).strftime(
                 "%Y-%m-%d %H:%M:%S")
-            print("Selecting data between %s and %s" % (s, e))
+            logger.debug("Selecting data between %s and %s" % (s, e))
             data = store.select("PSD", "(index >= '%s') & (index <= '%s')" % (s, e))
             data = store.PSD
             # only need to compute RMS for new/updated PSD data

msnoise/psd_export_rms.py

@@ -30,7 +30,7 @@ def main(loglevel="INFO", njobs_per_worker=9999):
     params = get_params(db)
     files = glob.glob(os.path.join("PSD", "RMS", params.qc_rms_type, '*.h5'))
     for file in sorted(files):
-        print(file)
+        logger.debug(file)
         store = hdf_open_store_from_fn(file, "r")\
 
         store.RMS.to_csv(file.replace(".h5", ".csv"))

msnoise/psd_to_hdf.py

@@ -44,7 +44,7 @@ def main(loglevel="INFO", njobs_per_worker=9999):
         for job in jobs:
             net, sta, loc = job.pair.split('.')
             if station is None:
-                print("Processing %s" % (job.pair))
+                logger.debug("Processing %s" % (job.pair))
                 station = get_station(db, net, sta)
             for chan in station.chans():
                 if chan not in datelists: