pymast 0.0.1__py3-none-any.whl → 0.0.3__py3-none-any.whl

pymast/__init__.py

@@ -14,9 +14,8 @@ from .overlap_removal import *
 from .parsers import *
 
 # Finally, import the radio_project class, which depends on parsers, predictor, and naive_bayes
-<<<<<<< Updated upstream:mast/__init__.py
-from .radio_project import *
-=======
+
 from .radio_project import *
 
->>>>>>> Stashed changes:biotas_refactor/__init__.py
+
+

pymast/formatter.py

@@ -15,7 +15,7 @@ import sqlite3
 import datetime
 from matplotlib import rcParams
 from scipy import interpolate
-from mast.radio_project import radio_project
+from pymast.radio_project import radio_project
 
 
 font = {'family': 'serif','size': 6}
@@ -43,15 +43,19 @@ class cjs_data_prep():
             query_parts.append(f"rec_id == '{key}'")   
         qry = " & ".join(query_parts)
 
-        recap_data = pd.read_hdf(project.db,
-                             'recaptures',
-                             where = qry)
+        self.recap_data = pd.read_hdf(project.db,
+                             'recaptures')#, 
+                             #where = qry)
         
-        self.recap_data.set_index('freq_code', inplace = True)
-        project.tags.set_index('freq_code', inplace = True)
-        self.recap_data = pd.merge(recap_data, project.tags, how = 'left')
+        #self.recap_data.set_index('freq_code', inplace = True)
+        project.tags.reset_index('freq_code', inplace = True)
+        self.recap_data = pd.merge(self.recap_data, 
+                                   project.tags,
+                                   left_on = 'freq_code', 
+                                   right_on = 'freq_code',
+                                   how = 'left')
         self.recap_data.reset_index(drop = False, inplace = True)
-        project.tags.reset_index(drop = False, inplace = True)
+        #project.tags.reset_index(drop = False, inplace = True)
         
         # filter out tag data we don't want mucking up our staistical model
         if species != None:
@@ -77,46 +81,42 @@ class cjs_data_prep():
             '''
 
             print ("Adding release time for this fish")
-            sql = "SELECT FreqCode, TagType, RelDate, RelLoc, CapLoc FROM tblMasterTag WHERE TagType = 'Study'"
-            relDat = pd.read_sql_query(sql,con = conn, parse_dates = 'RelDate')
+            rel_dat = project.tags
             if self.rel_loc is not None:
-                relDat = relDat[relDat.RelLoc == rel_loc]
+                rel_dat = rel_dat[rel_dat.rel_loc == rel_loc]
             if self.cap_loc is not None:
-                relDat = relDat[relDat.CapLoc == cap_loc]
-            relDat['RelDate'] = pd.to_datetime(relDat.RelDate)
-            relDat['Epoch'] = (relDat['RelDate'] - datetime.datetime(1970,1,1)).dt.total_seconds()
-            relDat.rename(columns = {'RelDate':'timeStamp'}, inplace = True)
-            relDat['RecapOccasion'] = np.repeat('R00',len(relDat))
-            #relDat.dropna(inplace =True)
-            relDat['overlapping'] = np.zeros(len(relDat))
-            self.data = self.data.append(relDat)
-
+                rel_dat = rel_dat[rel_dat.cap_loc == cap_loc]
+            rel_dat['rel_date'] = pd.to_datetime(rel_dat.rel_date)
+            rel_dat['epoch'] = (rel_dat['rel_date'] - datetime.datetime(1970,1,1)).dt.total_seconds()
+            rel_dat.rename(columns = {'rel_date':'time_stamp'}, inplace = True)
+            rel_dat['recap_occasion'] = np.repeat('R00',len(rel_dat))
+            rel_dat['overlapping'] = np.zeros(len(rel_dat))
+            self.recap_data = pd.concat([self.recap_data,rel_dat],axis = 0)
 
         else:
             print ("Starting Initial Recap Release Procedure")
             # Identify first recapture times
-            startTimes = self.data[self.data.RecapOccasion == "R00"].groupby(['FreqCode'])['Epoch'].min().to_frame()
-            startTimes.reset_index(drop = False, inplace = True)
-            startTimes.set_index('FreqCode',inplace = True)
-            startTimes.rename(columns = {'Epoch':'FirstRecapture'},inplace = True)
+            start_times = self.recap_data[self.recap_data.recap_occasion == "R00"].groupby(['freq_code'])['epoch'].min().to_frame()
+            start_times.reset_index(drop = False, inplace = True)
+            start_times.set_index('freq_code',inplace = True)
+            start_times.rename(columns = {'epoch':'first_recapture'},inplace = True)
 
             # make sure fish start from the first recapture occassion and that there are no recaps before release
-            for fish in self.data.FreqCode.unique():
+            for fish in self.recap_data.freq_code.unique():
 
-                if fish not in startTimes.index.values:
+                if fish not in start_times.index.values:
                     # fish never made it to the initial state
-                    self.data.drop(self.data[self.data.FreqCode == fish].index, inplace = True)
+                    self.recap_data.drop(self.recap_data[self.recap_data.freq_code == fish].index, inplace = True)
                 else:
                     # fish arrived at the initial state but their may be recaptures before arrival at initial state
-                    t = startTimes.at[fish,'FirstRecapture']
-                    self.data.drop(self.data[(self.data.FreqCode == fish) & (self.data.Epoch < t)].index, inplace = True)
+                    t = start_times.at[fish,'first_recapture']
+                    self.recap_data.drop(self.recap_data[(self.recap_data.freq_code == fish) & (self.recap_data.epoch < t)].index, inplace = True)
 
-        print (self.data.head())
-        c.close()
+        print (self.recap_data.head())
 
-    def input_file(self,modelName, outputWS):
+    def input_file(self,model_name, output_ws):
         #Step 1: Create cross tabulated data frame with FreqCode as row index and recap occasion as column
-        cross_tab = pd.pivot_table(self.data, values = 'Epoch', index = 'FreqCode', columns = 'RecapOccasion', aggfunc = 'min')
+        cross_tab = pd.pivot_table(self.recap_data, values = 'epoch', index = 'freq_code', columns = 'recap_occasion', aggfunc = 'min')
 
         #Step 2: Fill in those nan values with 0, we can't perform logic on nothing!'''
         cross_tab.fillna(value = 0, inplace = True)
@@ -134,7 +134,7 @@ class cjs_data_prep():
         self.cross = cross_tab
         # Check your work
         print (cross_tab.head(100))
-        cross_tab.to_csv(os.path.join(outputWS,'%s_cjs.csv'%(modelName)))
+        cross_tab.to_csv(os.path.join(output_ws,'%s_cjs.csv'%(model_name)))
 
 class lrdr_data_prep():
     '''Class creates input files for Live Recapture Dead Recovery modeling in MARK'''

pymast/parsers.py

@@ -4,7 +4,7 @@ import pandas as pd
 import numpy as np
 import datetime
 import os
-import mast.predictors as predictors
+import pymast.predictors as predictors
 
 def ares(file_name, 
                  db_dir, 
@@ -222,7 +222,7 @@ def orion_import(file_name,
                     
                     telem_dat_sub = telem_dat_sub.astype({'power':'float32',
                                                           'freq_code':'object',
-                                                          'time_stamp':'datetime64',
+                                                          'time_stamp':'datetime64[ns]',
                                                           'scan_time':'float32',
                                                           'channels':'int32',
                                                           'rec_type':'object',
@@ -495,7 +495,7 @@ def srx1200(file_name,
         # format frequency code
         telem_dat['FreqNo'] = telem_dat['Freq [MHz]'].apply(lambda x: f"{x:.3f}" )
         telem_dat = telem_dat[telem_dat['Tag/BPM'] != 999]
-        telem_dat['freq_code'] = telem_dat['FreqNo'] + ' ' + telem_dat['Tag/BPM'].astype(np.str)
+        telem_dat['freq_code'] = telem_dat['FreqNo'] + ' ' + telem_dat['Tag/BPM'].astype(str)
         
         # calculate 
         telem_dat['noise_ratio'] = predictors.noise_ratio(600,
@@ -572,7 +572,7 @@ def srx1200(file_name,
         telem_dat['FreqNo'] = telem_dat['Freq [MHz]'].apply(lambda x: f"{x:.3f}" )
         telem_dat = telem_dat[telem_dat['TagID/BPM'] != 999]
 
-        telem_dat['freq_code'] = telem_dat['FreqNo'] + ' ' + telem_dat['TagID/BPM'].astype(np.str)
+        telem_dat['freq_code'] = telem_dat['FreqNo'] + ' ' + telem_dat['TagID/BPM'].astype(str)
         
         # calculate 
         telem_dat['noise_ratio'] = predictors.noise_ratio(600,
@@ -741,7 +741,7 @@ def srx800(file_name,
         split = setup_df['change_date'].str.split(' ', expand=True)
         setup_df['day0'] = np.repeat(pd.to_datetime("1900-01-01"),len(setup_df))
         setup_df['Date'] = setup_df['day0'] + pd.to_timedelta(split[1].astype(int), unit='d')
-        setup_df['change_date'] = setup_df.Date.astype(np.str) + ' ' + split[2]
+        setup_df['change_date'] = setup_df.Date.astype(str) + ' ' + split[2]
         
 
     setup_df['change_date'] = pd.to_datetime(setup_df.change_date)
@@ -851,8 +851,11 @@ def srx800(file_name,
             telem_dat_sub['epoch'] = np.round((telem_dat_sub.time_stamp - pd.Timestamp("1970-01-01")) / pd.Timedelta('1s'),6)
             
             # get setup number for every row
-            telem_dat_sub['setup'] = get_setup(telem_dat_sub.epoch.values,
-                                               setup_df.epoch.values)
+            try:
+                telem_dat_sub['setup'] = get_setup(telem_dat_sub.epoch.values,
+                                                   setup_df.epoch.values)
+            except:
+                print ('why you fail?')
             
             # get frequency from channel
             telem_dat_sub['Frequency'] = get_frequency(telem_dat_sub.setup.values,
@@ -890,7 +893,7 @@ def srx800(file_name,
             # write to hdf
             telem_dat_sub = telem_dat_sub.astype({'power':'float32',
                                                   'freq_code':'object',
-                                                  'time_stamp':'datetime64',
+                                                  'time_stamp':'datetime64[ns]',
                                                   'scan_time':'float32',
                                                   'channels':'int32',
                                                   'rec_type':'object',

pymast/predictors.py

@@ -121,6 +121,7 @@ def detection_history (epoch, pulse_rate, num_detects, num_channels, scan_time,
             lower_limit_dict[i] = np.where(scan_time > 2 * pulse_rate,
                                            epoch + (pulse_rate * i - 1),
                                            epoch + ((scan_time * channels * i) - 1))
+
             upper_limit_dict[i] = np.where(scan_time > 2 * pulse_rate, 
                                            epoch + (pulse_rate * i + 1),
                                            epoch + ((scan_time * channels * i) + 1))

pymast/radio_project.py

@@ -9,9 +9,9 @@ import pandas as pd
 import os
 import h5py
 import datetime
-import mast.naive_bayes as naive_bayes
-import mast.parsers as  parsers
-import mast.predictors as predictors
+import pymast.naive_bayes as naive_bayes
+import pymast.parsers as  parsers
+import pymast.predictors as predictors
 import matplotlib.pyplot as plt
 from matplotlib import rcParams
 from scipy import interpolate
@@ -295,7 +295,7 @@ class radio_project():
         # make sure data types are correct - these next steps are critical
         try:
             train_dat = train_dat.astype({'power': 'float32', 
-                                          'time_stamp': 'datetime64',
+                                          'time_stamp': 'datetime64[ns]',
                                           'epoch': 'float32',
                                           'freq_code': 'object',
                                           'noise_ratio': 'float32',
@@ -486,12 +486,8 @@ class radio_project():
                           min_itemsize = {'freq_code':20,
                                           'rec_type':20,
                                           'rec_id':20,
-<<<<<<< Updated upstream:mast/radio_project.py
                                           'det_hist':20})      
-=======
-                                          'det_hist':20})  
->>>>>>> Stashed changes:biotas_refactor/radio_project.py
-                
+
     def undo_import(self, rec_id):
         # Read the table from the HDF5 file
         with pd.HDFStore(self.db, 'r+') as store:
@@ -712,7 +708,7 @@ class radio_project():
             class_dat = class_dat.astype({'freq_code': 'object',
                                           'epoch': 'float32',
                                           'rec_id': 'object',
-                                          'time_stamp': 'datetime64',
+                                          'time_stamp': 'datetime64[ns]',
                                           'power': 'float32', 
                                           'noise_ratio': 'float32',
                                           'scan_time': 'int32',
@@ -1133,7 +1129,7 @@ class radio_project():
                         rec_dat = rec_dat.astype({'freq_code': 'object',
                                                 'epoch': 'float32',
                                                 'rec_id': 'object',
-                                                'time_stamp': 'datetime64',
+                                                'time_stamp': 'datetime64[ns]',
                                                 'power': 'float32', 
                                                 'noise_ratio': 'float32',
                                                 'lag': 'float32',
@@ -1167,4 +1163,4 @@ class radio_project():
                 
 
             
-                    
+                    

{pymast-0.0.1.dist-info → pymast-0.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pymast
-Version: 0.0.1
+Version: 0.0.3
 Summary: Movement Analysis Software for Telemetry (MAST) for
 Home-page: https://github.com/knebiolo/mast
 Author: Kevin P. Nebiolo and Theodore Castro-Santos

pymast-0.0.3.dist-info/RECORD

@@ -0,0 +1,14 @@
+pymast/__init__.py,sha256=lvDHHvhI7UL2F5QLDU_2b62OUnRTlhybslr6aTn27Z0,538
+pymast/fish_history.py,sha256=XaubGDRLfR89v2rIrFvkf7AKOLMTA5z--KyCJoXqnv4,6822
+pymast/formatter.py,sha256=Iq0VYtA-U7j7z7e-5H1OfRd0uP5dod2ptOKs2GK8hlc,58555
+pymast/naive_bayes.py,sha256=pjB8LSIFM8-fW7sohy5gCuFgKk1VP5yh63raMp9mdEU,6475
+pymast/overlap_removal.py,sha256=4SwP8qZDqEYZ6_I0xGlI6647bTt45EaGDP5FxbqddZo,25416
+pymast/parsers.py,sha256=WNIp-D8P0978SjZlQbur9BZ5iY27AnTTaQUELWapMRI,59220
+pymast/predictors.py,sha256=VEWnhxgJcbnag8h6DNpWbeWgGiK9YyV_3N4xkcJFjdo,8018
+pymast/radio_project.py,sha256=QT9l_qyZTKWqTu55kpgIESPDR1dnjajEQlUBYSg0H8Q,55502
+pymast/table_merge.py,sha256=7_z4F_q3DW3RFXruRH6Qanum7E5QQQnu_w6qyyW-YVc,7921
+pymast-0.0.3.dist-info/LICENSE.txt,sha256=CX_nvzXXwOA7SPq4-ivN4Q9NIK2PfK-KGHt3ZQKldsw,1143
+pymast-0.0.3.dist-info/METADATA,sha256=lpPvKs8ks4V3nLe6Zx6ROdXxeN7_69THPm_ngfBYBF8,572
+pymast-0.0.3.dist-info/WHEEL,sha256=yQN5g4mg4AybRjkgi-9yy4iQEFibGQmlz78Pik5Or-A,92
+pymast-0.0.3.dist-info/top_level.txt,sha256=LDZpLLge9zI4yvuMYoABLrsOrZzE3bYDRULmHoZQc4k,7
+pymast-0.0.3.dist-info/RECORD,,

{pymast-0.0.1.dist-info → pymast-0.0.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: bdist_wheel (0.41.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

pymast-0.0.1.dist-info/RECORD

@@ -1,14 +0,0 @@
-pymast/__init__.py,sha256=c5E_2yJ_rNRScps1oZDeDDbMmIg-9EhEJXHlT5Kr83s,667
-pymast/fish_history.py,sha256=XaubGDRLfR89v2rIrFvkf7AKOLMTA5z--KyCJoXqnv4,6822
-pymast/formatter.py,sha256=ayiiEkXWEM91FUXF1E1qd3kZOHPMJ2irzoHiDJG3ymY,58422
-pymast/naive_bayes.py,sha256=pjB8LSIFM8-fW7sohy5gCuFgKk1VP5yh63raMp9mdEU,6475
-pymast/overlap_removal.py,sha256=4SwP8qZDqEYZ6_I0xGlI6647bTt45EaGDP5FxbqddZo,25416
-pymast/parsers.py,sha256=rTccM2QMIw7YBuBljyftuyiFiaXZXPfDz6jMrOA3ygA,59131
-pymast/predictors.py,sha256=Nxbq9MdX4hru9ZiVdSneYKovpspJPjs3LA-SKCJxuLM,8016
-pymast/radio_project.py,sha256=mFJlPkoq30n7I5YOV0QBH-NQVZS6YObxG14Db7mC5aE,55674
-pymast/table_merge.py,sha256=7_z4F_q3DW3RFXruRH6Qanum7E5QQQnu_w6qyyW-YVc,7921
-pymast-0.0.1.dist-info/LICENSE.txt,sha256=CX_nvzXXwOA7SPq4-ivN4Q9NIK2PfK-KGHt3ZQKldsw,1143
-pymast-0.0.1.dist-info/METADATA,sha256=G8LRwAQXKnjS_RC58imwpHgKq5843Dt889LA_atmKB4,572
-pymast-0.0.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-pymast-0.0.1.dist-info/top_level.txt,sha256=LDZpLLge9zI4yvuMYoABLrsOrZzE3bYDRULmHoZQc4k,7
-pymast-0.0.1.dist-info/RECORD,,