Many minor code changes

Author: ifeoluwaale

.github/workflows/run_tests.yml

@@ -18,11 +18,20 @@ jobs:
           python-version: ${{ matrix.python-version }}
       - name: Display Python version
         run: python -c "import sys; print(sys.version)"
+      - name: Build dplpy
+        run: |
+          python -m pip install -U pip build
+          python -m build
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r ${{ matrix.python-version }}-requirements.txt
           pip install pytest pytest-cov
+          pip install ruff
+      - name: Lint with Ruff
+        run: |
+          ruff --output-format=github .
+        continue-on-error: true
       - name: Run unit tests
         run: |
           pytest tests/unit --cov=dplpy

dplpy/autoreg.py

@@ -158,7 +158,6 @@ def autoreg(data: pd.Series, max_lag=5):
 # given an array containing the original data and the parameters for
 # the AR model
 def fitted_values(data_series, params):
-    mean = np.mean(data_series)
     results = []
 
     for i in range((len(params)-1), len(data_series)):

dplpy/chron.py

@@ -167,7 +167,7 @@ def plot_chron(years, depths, means, whitened_means):
     # create figure and axis objects with subplots()
     fig,ax = plt.subplots()
 
-    if whitened_means != None:
+    if whitened_means is not None:
         y_val = whitened_means
         y_label = "Mean Res"
     else:

dplpy/create_json.py

@@ -33,97 +33,97 @@
 
 def create_json(input):
 
-with open("input", "r" ) as rings:
-    data= rings.read()
-    lines = data.split("\n")
-    print (lines[0-2])
-    # read every single line
-    for  rows  in lines:
-        print (rows)
+    with open("input", "r" ) as rings:
+        data= rings.read()
+        lines = data.split("\n")
+        print (lines[0-2])
+        # read every single line
+        for  rows  in lines:
+            print (rows)
+        
+        # remove empty lines from the file.
+
+        # convert every element in each list to string- it is easier to manupilate the elements
+
+        for items in lines:
+            str(items)  
+
+        # State/province
+        state_province = lines[1,3]
+
+        # country
+        country= lines[0,2]
+
+        # species
+        species = lines[1,4]
+
+        # species code
+        species_code= lines[1,5]
+
+        # start year- start of collection 
+        start_date = int(lines[1,6])
+
+        # end year- completion year
+        end_year = int(lines[1,7])
+
+    # latitude, longitude, elevation 
+        latitude = lines[2,4]
+        longitude = lines[2,5]
+
+        # lead investigator
+        lead_investigator= lines[2,2] 
+
+        # site_id
+            # Via indexing the first three digits of the site id are assigned to var named site_code and the rest to information.
+            # Check if all the site codes are the same for the whole dataset 
+        for site_code in lines:
+            current=0
+            information=0 
+            site_id=0 
+            unit = 0
+            while current >=0 and current<=len(lines)-1:
+                if current <=3:   
+                    site_code = lines[current,0,0]       
+                if current>=4 and current<=len(lines)-1:
+                    if lines[current,0,0] == lines[4,0,0]:
+                        site_id = lines[current,0,0]
+                        information = site_id[3::]  
+                site_id= site_code + information 
+                #data
+                data=[]
+                y=1
+                past= y-1
+                end=[current,-1]
+                if site_id == lines[current,0] and start_date <= int(lines[current]):
+                    for points in lines[current,2:]:
+                        pts=[]
+                        pts.append(points)
+                        # End of data collection for that year
+                        if points== "999" or points== "-9999":
+                            pts[:-1]
+                            data.append(pts)
+                            pts=0
+                            unit = points
+                else:
+                    current = current + 1
+                    pts=0
 
-    # remove empty lines from the file.
-
-    # convert every element in each list to string- it is easier to manupilate the elements
-
-    for items in lines:
-        str(items)  
-
-    # State/province
-    state_province = lines[1,3]
-
-    # country
-    country= lines[0,2]
-
-    # species
-    species = lines[1,4]
-
-    # species code
-    species_code= lines[1,5]
-
-    # start year- start of collection 
-    start_date = int(lines[1,6])
-
-    # end year- completion year
-    end_year = int(lines[1,7])
-
-# latitude, longitude, elevation 
-    latitude = lines[2,4]
-    longitude = lines[2,5]
-
-    # lead investigator
-    lead_investigator= lines[2,2] 
-
-    # site_id
-        # Via indexing the first three digits of the site id are assigned to var named site_code and the rest to information.
-        # Check if all the site codes are the same for the whole dataset 
-    for site_code in lines:
-        current=0
-        information=0 
-        site_id=0 
-        unit = 0
-        while current >=0 and current<=len(lines)-1:
-            if current <=3:   
-                site_code = lines[current,0,0]       
-            if current>=4 and current<=len(lines)-1:
-                if lines[current,0,0] == lines[4,0,0]:
-                    site_id = lines[current,0,0]
-                    information = site_id[3::]  
-            site_id= site_code + information 
-            #data
-            data=[]
-            y=1
-            past= y-1
-            end=[current,-1]
-            if site_id == lines[current,0] and start_date <= int(lines[]):
-                for points in lines[current,2:]:
-                    pts=[]
-                    pts.append(points)
-                    # End of data collection for that year
-                    if points== "999" or points== "-9999":
-                        pts[:-1]
-                        data.append(pts)
-                        pts=0
-                        unit = points
-            else:
-                current = current + 1
-                pts=0
-   
-jsonfile = {}
-jsonfile["site_code"] = site_code
-jsonfile["site_name"] = site_id
-jsonfile["species_code"] = species_code
-jsonfile["species_name"] = species
-jsonfile["country"] = country
-jsonfile["state_province"] = state_province
-jsonfile["elevation"] = ""
-jsonfile["latitude"] = latitude
-jsonfile["longitude"] = longitude
-if unit == "999":
-    jsonfile["unit"] = "0.01mm"
-elif unit == "-9999":
-    jsonfile["unit"] = "0.001mm"
-else:
-    print("ERROR - Stop code is not 999 or -9999. Cannot identify a unit.")
-    exit
-jsonfile["lead_investigator"] = lead_investigator
-jsonfile["collection_date"] = ""
+    jsonfile = {}
+    jsonfile["site_code"] = site_code
+    jsonfile["site_name"] = site_id
+    jsonfile["species_code"] = species_code
+    jsonfile["species_name"] = species
+    jsonfile["country"] = country
+    jsonfile["state_province"] = state_province
+    jsonfile["elevation"] = ""
+    jsonfile["latitude"] = latitude
+    jsonfile["longitude"] = longitude
+    if unit == "999":
+        jsonfile["unit"] = "0.01mm"
+    elif unit == "-9999":
+        jsonfile["unit"] = "0.001mm"
+    else:
+        print("ERROR - Stop code is not 999 or -9999. Cannot identify a unit.")
+        exit
+    jsonfile["lead_investigator"] = lead_investigator
+    jsonfile["collection_date"] = ""

dplpy/curvefit.py

@@ -29,7 +29,6 @@
 #              modified negative exponential, linear and horizontal.
 
 import numpy as np
-import pandas as pd
 from scipy.optimize import curve_fit
 
 # Modified hugershoff function

dplpy/detrend.py

@@ -28,11 +28,9 @@
 #              with spline(s) as the default, and then by calculating residuals or differences 
 #              compared to the original data (residuals by default).
 
-from tkinter import Y
 import pandas as pd
 import matplotlib.pyplot as plt
 from smoothingspline import spline
-from autoreg import ar_func
 import curvefit
 
 def detrend(data: pd.DataFrame | pd.Series, fit="spline", method="residual", plot=True, period=None):
@@ -141,7 +139,10 @@ def detrend_series(data: pd.Series, fit, method, plot, period=None):
 
         plt.show()
 
-    return pd.Series(detrended_data, index=x, name=series_name)
+    return pd.Series(detrended_data, index=pd.Index(data=x, name="Year"), name=series_name).combine(data, pick_first)
+
+def pick_first(a, b):
+    return a
 
 # Detrends by finding ratio of original series data to curve data
 def residual(y, yi):

dplpy/dplpy.py

@@ -1,4 +1,17 @@
 from __future__ import print_function
+from readers import readers
+from summary import summary
+from stats import stats
+from report import report
+from plot import plot
+from detrend import detrend
+from autoreg import ar_func, autoreg
+from chron import chron
+from chron_stabilized import chron_stabilized
+from xdate import xdate
+from series_corr import series_corr
+from writers import write
+
 
 __copyright__ = """
    dplPy for tree ring width time series analyses
@@ -93,7 +106,7 @@ def readme():
     try:
         a = webbrowser.open("https://opendendro.org/dplpy-man/", new=2)
         print("Success: Check your web browser for a new tab")
-        if a == False:
+        if a is False:
             print("Your computer does not use a monitor, and cannot display the webpages")
     except Exception as e:
         print(e)
@@ -143,18 +156,6 @@ def readme_from_parser(args):
 #
 #dplpy_version()
 
-from readers import readers
-from summary import summary
-from stats import stats
-from report import report
-from plot import plot
-from detrend import detrend
-from autoreg import ar_func, autoreg
-from chron import chron
-from chron_stabilized import chron_stabilized
-from xdate import xdate, xdate_plot
-from series_corr import series_corr
-from writers import write
 
 
 # set the definition for the Readers functions (from readers.py)
@@ -203,17 +204,6 @@ def chron_stabilized_from_parser(args):
 def write_from_parser(args):
     write(input=args.input)
 
-def series_corr_from_parser(args):
-    series_corr(input=args.input)
-
-def series_corr_from_parser(args):
-    series_corr(input=args.input)
-
-def common_interval_from_parser(args):
-    common_interval(input=args.input)
-
-def rbar_from_parser(args):
-    rbar(input=args.input)
 # creates whitespace
 print("")
 

dplpy/rbar.py

@@ -28,7 +28,6 @@
 #              period of years, and calculating rbar constant for a dataset over this best
 #              period of overlap
 
-import pandas as pd
 import numpy as np
 from detrend import detrend
 from chron import chron