tsp 1.7.3__py3-none-any.whl → 1.7.7__py3-none-any.whl

tsp/scratch.py

@@ -0,0 +1,6 @@
+from tsp import read_geotop
+
+t = read_geotop(r"C:\Users\Nick\Desktop\soil0032.txt")
+import pdb;pdb.set_trace()
+
+print('ok')

tsp/time.py

@@ -1,46 +1,46 @@
-import re
-from datetime import datetime, tzinfo
-
-from typing import Union
-
-
-def get_utc_offset(offset: "Union[str,int]") -> int:
-    """Get the UTC offset in seconds from a string or integer"""
-
-    if isinstance(offset, str):
-        if offset.lower() == "utc" or (offset.lower() == "z"):
-            return 0
-        
-        pattern = re.compile(r"([+-]?)(\d{2}):(\d{2})")
-        match = pattern.match(offset)
-        
-        if not match:
-            raise ValueError("Offset must be a string in the format '+HH:MM' or '-HH:MM'")
-        
-        sign = match.group(1)
-        hours = int(match.group(2))
-        minutes = int(match.group(3))
-        utc_offset = (hours*60 + minutes)*60
-        if sign == "-":
-            utc_offset *= -1
-
-    elif isinstance(offset, int):
-        utc_offset = offset
-
-    else:
-        raise ValueError("Offset must be a string in the format '+HH:MM' or '-HH:MM' or an integer in seconds")
-
-    return utc_offset
-
-
-def format_utc_offset(offset: tzinfo) -> str:
-    """Format a UTC offset as a string in the format '+HH:MM' or '-HH:MM'"""
-    utc_offset = offset.utcoffset(datetime.now()).total_seconds()
-    sign = "-" if utc_offset < 0 else "+"
-    hours = int(abs(utc_offset)//3600)
-    minutes = int(abs(utc_offset)%3600/60)
-    
-    if hours == 0 and minutes == 0:
-        return "UTC"
-
+import re
+from datetime import datetime, tzinfo
+
+from typing import Union
+
+
+def get_utc_offset(offset: "Union[str,int]") -> int:
+    """Get the UTC offset in seconds from a string or integer"""
+
+    if isinstance(offset, str):
+        if offset.lower() == "utc" or (offset.lower() == "z"):
+            return 0
+        
+        pattern = re.compile(r"([+-]?)(\d{2}):(\d{2})")
+        match = pattern.match(offset)
+        
+        if not match:
+            raise ValueError("Offset must be a string in the format '+HH:MM' or '-HH:MM'")
+        
+        sign = match.group(1)
+        hours = int(match.group(2))
+        minutes = int(match.group(3))
+        utc_offset = (hours*60 + minutes)*60
+        if sign == "-":
+            utc_offset *= -1
+
+    elif isinstance(offset, int):
+        utc_offset = offset
+
+    else:
+        raise ValueError("Offset must be a string in the format '+HH:MM' or '-HH:MM' or an integer in seconds")
+
+    return utc_offset
+
+
+def format_utc_offset(offset: tzinfo) -> str:
+    """Format a UTC offset as a string in the format '+HH:MM' or '-HH:MM'"""
+    utc_offset = offset.utcoffset(datetime.now()).total_seconds()
+    sign = "-" if utc_offset < 0 else "+"
+    hours = int(abs(utc_offset)//3600)
+    minutes = int(abs(utc_offset)%3600/60)
+    
+    if hours == 0 and minutes == 0:
+        return "UTC"
+
     return f"{sign}{hours:02d}:{minutes:02d}"

tsp/tspwarnings.py

@@ -0,0 +1,15 @@
+import numpy as np
+
+
+class DuplicateTimesWarning(UserWarning):
+    """For when duplicate times are found in a file."""
+    def __init__(self, times):
+        self.times = times
+    
+    def _msg(self, times) -> str:
+        m = f"Duplicate timestamps found: {times[np.where(times.duplicated())[0]]}. That's bad."
+        return m
+    
+    def __str__(self):
+        return self._msg(self.times)
+    

tsp/utils.py

@@ -1,101 +1,101 @@
-import pandas as pd
-import numpy as np
-
-import tsp
-from tsp import TSP
-
-
-def resolve_duplicate_times(t: TSP, keep="first") -> TSP:
-    """Eliminate duplicate times in a TSP.
-    
-    Parameters
-    ----------
-    tsp : TSP
-        TSP to resolve duplicate times in.
-    keep : str, optional
-        Method to resolve duplicate times. Chosen from "first", "average", "last", "strip"
-        by default "first"
-    
-    Returns
-    -------
-    TSP
-        TSP with no duplicated times."""
-    resolver = _get_duplicate_resolver(keep)
-    return resolver(t)
-    
-
-def _get_duplicate_resolver(keep: str):
-    if keep == "first":
-        return _first_duplicate_time
-    elif keep == "average":
-        return _average_duplicate_time
-    elif keep == "last":
-        return _last_duplicate_time
-    elif keep == "strip":
-        return _strip_duplicate_time
-    else:
-        raise ValueError(f"Unknown duplicate resolver method: {keep}")
-
-
-def _first_duplicate_time(t: TSP):
-    df = t.wide
-    df = df[~df.index.duplicated(keep="first")]
-    
-    time = df.index
-    values = df.drop(['time'], axis=1).values
-    depths = df.drop(['time'], axis=1).columns
-    
-    t_new = TSP(times=time, values=values, depths=depths, 
-                latitude=t.latitude, longitude=t.longitude,
-                site_id=t.site_id, metadata=t.metadata)
-    
-    return t_new
-
-
-def _last_duplicate_time(t: TSP):
-    df = t.wide
-    df = df[~df.index.duplicated(keep="last")]
-    
-    time = df.index
-    values = df.drop(['time'], axis=1).values
-    depths = df.drop(['time'], axis=1).columns
-    
-    t_new = TSP(times=time, values=values, depths=depths, 
-                latitude=t.latitude, longitude=t.longitude,
-                site_id=t.site_id, metadata=t.metadata)
-    
-    return t_new
-
-
-def _strip_duplicate_time(t: TSP):
-    df = t.wide
-    df = df[~df.index.duplicated(keep=False)]
-
-    time = df.index
-    values = df.drop(['time'], axis=1).values
-    depths = df.drop(['time'], axis=1).columns
-    
-    t_new = TSP(times=time, values=values, depths=depths, 
-                latitude=t.latitude, longitude=t.longitude,
-                site_id=t.site_id, metadata=t.metadata)
-    
-    return t_new
-
-
-def _average_duplicate_time(t: TSP):
-    singleton = t.wide[~t.wide.index.duplicated(keep=False)]
-    duplicated = t.wide[t.wide.index.duplicated(keep=False)].drop(['time'], axis=1).reset_index()
-    averaged = duplicated.groupby(duplicated['index']).apply(lambda x: x[~x.isna()].mean(numeric_only=True))  
-    averaged.insert(0, 'time',averaged.index)
-
-    df = pd.concat([singleton, averaged], ignore_index=False).sort_index()
-
-    time = df.index
-    values = df.drop(['time'], axis=1).values
-    depths = df.drop(['time'], axis=1).columns
-
-    t_new = TSP(times=time, values=values, depths=depths, 
-                latitude=t.latitude, longitude=t.longitude,
-                site_id=t.site_id, metadata=t.metadata)
-    
-    return t_new
+import pandas as pd
+import numpy as np
+
+import tsp
+from tsp import TSP
+
+
+def resolve_duplicate_times(t: TSP, keep="first") -> TSP:
+    """Eliminate duplicate times in a TSP.
+    
+    Parameters
+    ----------
+    tsp : TSP
+        TSP to resolve duplicate times in.
+    keep : str, optional
+        Method to resolve duplicate times. Chosen from "first", "average", "last", "strip"
+        by default "first"
+    
+    Returns
+    -------
+    TSP
+        TSP with no duplicated times."""
+    resolver = _get_duplicate_resolver(keep)
+    return resolver(t)
+    
+
+def _get_duplicate_resolver(keep: str):
+    if keep == "first":
+        return _first_duplicate_time
+    elif keep == "average":
+        return _average_duplicate_time
+    elif keep == "last":
+        return _last_duplicate_time
+    elif keep == "strip":
+        return _strip_duplicate_time
+    else:
+        raise ValueError(f"Unknown duplicate resolver method: {keep}")
+
+
+def _first_duplicate_time(t: TSP):
+    df = t.wide
+    df = df[~df.index.duplicated(keep="first")]
+    
+    time = df.index
+    values = df.drop(['time'], axis=1).values
+    depths = df.drop(['time'], axis=1).columns
+    
+    t_new = TSP(times=time, values=values, depths=depths, 
+                latitude=t.latitude, longitude=t.longitude,
+                site_id=t.site_id, metadata=t.metadata)
+    
+    return t_new
+
+
+def _last_duplicate_time(t: TSP):
+    df = t.wide
+    df = df[~df.index.duplicated(keep="last")]
+    
+    time = df.index
+    values = df.drop(['time'], axis=1).values
+    depths = df.drop(['time'], axis=1).columns
+    
+    t_new = TSP(times=time, values=values, depths=depths, 
+                latitude=t.latitude, longitude=t.longitude,
+                site_id=t.site_id, metadata=t.metadata)
+    
+    return t_new
+
+
+def _strip_duplicate_time(t: TSP):
+    df = t.wide
+    df = df[~df.index.duplicated(keep=False)]
+
+    time = df.index
+    values = df.drop(['time'], axis=1).values
+    depths = df.drop(['time'], axis=1).columns
+    
+    t_new = TSP(times=time, values=values, depths=depths, 
+                latitude=t.latitude, longitude=t.longitude,
+                site_id=t.site_id, metadata=t.metadata)
+    
+    return t_new
+
+
+def _average_duplicate_time(t: TSP):
+    singleton = t.wide[~t.wide.index.duplicated(keep=False)]
+    duplicated = t.wide[t.wide.index.duplicated(keep=False)].drop(['time'], axis=1).reset_index()
+    averaged = duplicated.groupby(duplicated['index']).apply(lambda x: x[~x.isna()].mean(numeric_only=True))  
+    averaged.insert(0, 'time',averaged.index)
+
+    df = pd.concat([singleton, averaged], ignore_index=False).sort_index()
+
+    time = df.index
+    values = df.drop(['time'], axis=1).values
+    depths = df.drop(['time'], axis=1).columns
+
+    t_new = TSP(times=time, values=values, depths=depths, 
+                latitude=t.latitude, longitude=t.longitude,
+                site_id=t.site_id, metadata=t.metadata)
+    
+    return t_new

tsp/version.py

@@ -1 +1 @@
-version="1.7.3"
+version="1.7.7"