Merge branch 'python-3.9' of 'https://github.com/jjmerchante/grimoirelab-cereslib'

Merges #64
Closes #64

Author: sduenas

.github/workflows/release.yml

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
       - name: Download distribution artifact

.github/workflows/tests.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
 
     name: Python ${{ matrix.python-version }}
     steps:

README.md

@@ -78,7 +78,7 @@ Those are probably a good place to have a look at.
 
 ## Requirements
 
- * Python >= 3.8
+ * Python >= 3.9
 
 You will also need some other libraries for running the tool, you can find the
 whole list of dependencies in [pyproject.toml](pyproject.toml) file.

cereslib/dfutils/format.py

@@ -22,7 +22,7 @@
 
 import pandas
 
-import scipy
+import numpy as np
 
 
 class Format(object):
@@ -53,7 +53,7 @@ def fill_missing_fields(self, data, columns):
 
         for column in columns:
             if column not in data.columns:
-                data[column] = scipy.zeros(len(data))
+                data[column] = np.zeros(len(data))
 
         return data
 

cereslib/enrich/enrich.py

@@ -83,16 +83,14 @@ def enrich(self, column1, column2):
            column2 not in self.commits.columns:
             return self.commits
 
-        # Select rows where values in column1 are different from
-        # values in column2
-        pair_df = self.commits[self.commits[column1] != self.commits[column2]]
-        new_values = list(pair_df[column2])
+        # Select rows where values in column1 are different from values in column2
+        pair_df = self.commits[self.commits[column1] != self.commits[column2]].copy()
+
         # Update values from column2
-        pair_df[column1] = new_values
+        pair_df[column1] = pair_df[column2].tolist()
 
-        # This adds at the end of the original dataframe those rows duplicating
-        # information and updating the values in column1
-        return self.commits.append(pair_df)
+        # Concatenate the original dataframe with the new one
+        return pandas.concat([self.commits, pair_df], ignore_index=True)
 
 
 class FileType(Enrich):
@@ -454,14 +452,14 @@ def __remove_surrogates(self, s, method='replace'):
         """ Remove surrogates in the specified string
         """
 
-        if type(s) == list and len(s) == 1:
+        if isinstance(s, list) and len(s) == 1:
             if self.__is_surrogate_escaped(s[0]):
                 return s[0].encode('utf-8', method).decode('utf-8')
             else:
                 return ""
-        if type(s) == list:
+        if isinstance(s, list):
             return ""
-        if type(s) != str:
+        if not isinstance(s, str):
             return ""
         if self.__is_surrogate_escaped(s):
             return s.encode('utf-8', method).decode('utf-8')

poetry.lock

@@ -41,16 +41,15 @@ classifiers = [
 "Bug Tracker" = "https://github.com/chaoss/grimoirelab-cereslib/issues"
 
 [tool.poetry.dependencies]
-python = "^3.8"
+python = "^3.9"
 
-numpy = "<1.22.1"
 six = "^1.16.0"
 scipy = "^1.5"
-pandas = "^1.3.5"
+pandas = "^2.2"
 grimoirelab-toolkit = { version = ">=0.3", allow-prereleases = true }
 
 [tool.poetry.dev-dependencies]
-flake8 = "^4.0.1"
+flake8 = "^7.1.1"
 coverage = "^6.2"
 
 [build-system]

pyproject.toml

@@ -0,0 +1,8 @@
+---
+title: Python minimum version updated
+category: dependency
+author: Jose Javier Merchante <jjmerchante@bitergia.com>
+issue: null
+notes: >
+  Python 3.8 will reach its end of life in October 2024.
+  Python 3.9 is the minimum version required by the project.

releases/unreleased/python-minimum-version-updated.yml

@@ -40,7 +40,7 @@ def test_filter_rows(self):
 
         # One column, values of different types
         df = pandas.DataFrame()
-        filepaths = ['', None, '-', '/file/path', 1, True, pandas.np.nan, '-', [1, 2]]
+        filepaths = ['', None, '-', '/file/path', 1, True, pandas.NA, '-', [1, 2]]
         df["filepath"] = filepaths
         data_filtered = FilterRows(df)
         df = data_filtered.filter_(["filepath"], "-")

tests/test_filter.py

@@ -23,7 +23,8 @@
 import unittest
 
 import pandas
-import scipy
+
+import numpy as np
 
 if '..' not in sys.path:
     sys.path.insert(0, '..')
@@ -50,7 +51,7 @@ def test_fill_missing_fields(self):
 
         # With a dataframe with some data, this returns a non-empty dataframe
         df = empty_df.copy()
-        df["test"] = scipy.zeros(10)
+        df["test"] = np.zeros(10)
 
         self.assertFalse(Format().fill_missing_fields(df, empty_columns).empty)