Add tests to excel in report datasets

benchmark/Results.py

@@ -580,7 +580,7 @@ class ReportDatasets:
     color2 = "#FDE9D9"
     color3 = "#B1A0C7"
 
-    def __init__(self, excel, book=None):
+    def __init__(self, excel=False, book=None):
         self.excel = excel
         self.env = EnvData().load()
         self.close = False
@@ -589,7 +589,7 @@ class ReportDatasets:
         if excel:
             self.max_length = 0
             if book is None:
-                self.excel_file_name = "ReportDatasets.xlsx"
+                self.excel_file_name = Files.datasets_report_excel
                 self.book = xlsxwriter.Workbook(
                     self.excel_file_name, {"nan_inf_to_errors": True}
                 )
@@ -728,6 +728,7 @@ class ReportDatasets:
         self.sheet.write(
             4, 4, f"{self.env['seeds']}", merge_format_subheader_left
         )
+        self.update_max_length(len(self.env["seeds"]) + 1)
         header_cols = [
             ("Dataset", 30),
             ("Samples", 10),
@@ -775,10 +776,13 @@ class ReportDatasets:
         self.sheet.write(self.row, col + 2, result.features, integer)
         self.sheet.write(self.row, col + 3, result.classes, normal)
         self.sheet.write(self.row, col + 4, result.balance, normal)
-        if len(result.balance) > self.max_length:
+        self.update_max_length(len(result.balance))
-            self.max_length = len(result.balance)
         self.row += 1
 
+    def update_max_length(self, value):
+        if value > self.max_length:
+            self.max_length = value
+
     def report(self):
         data_sets = Datasets()
         color_line = TextColor.LINE1
@@ -789,7 +793,7 @@ class ReportDatasets:
             print(self.header_text)
             print("")
             print(f"{'Dataset':30s} Sampl. Feat. Cls Balance")
-            print("=" * 30 + " ===== ====== === " + "=" * 60)
+            print("=" * 30 + " ====== ===== === " + "=" * 60)
         for dataset in data_sets:
             attributes = data_sets.get_attributes(dataset)
             attributes.dataset = dataset
@@ -1255,8 +1259,7 @@ class Benchmark:
             sheet.merge_range(row, 0, row + 1, 0, "Model", merge_format)
             sheet.merge_range(row, 1, row + 1, 5, "File", merge_format)
             sheet.merge_range(row, 6, row + 1, 6, "Score", merge_format)
-            sheet.freeze_panes(6, 1)
+            row += 1
-            sheet.hide_gridlines(2)
             d_name = next(iter(self._datasets))
             for model in self._models:
                 file_name = self._report[model][d_name]["file_name"]
@@ -1280,7 +1283,10 @@ class Benchmark:
                 )
                 k = Excel(file_name=file_name, book=book)
                 k.report()
+            sheet.freeze_panes(6, 1)
+            sheet.hide_gridlines(2)
 
+        def add_datasets_sheet():
             # Add datasets sheet
             re = ReportDatasets(excel=True, book=book)
             re.report()
@@ -1311,6 +1317,7 @@ class Benchmark:
         footer()
         models_files()
         exreport_output()
+        add_datasets_sheet()
         book.close()
 
 

benchmark/Utils.py

@@ -27,6 +27,7 @@ class Files:
     exreport_pdf = "Rplots.pdf"
     benchmark_r = "benchmark.r"
     dot_env = ".env"
+    datasets_report_excel = "ReportDatasets.xlsx"
 
     @staticmethod
     def exreport_output(score):

benchmark/tests/.env

@@ -6,3 +6,4 @@ stratified=0
 # Source of data Tanveer/Surcov
 source_data=Tanveer
 seeds=[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]
+discretize=0

benchmark/tests/.gitignore

@@ -0,0 +1 @@
+ReportDatasets.xlsx 

benchmark/tests/Benchmark_test.py

@@ -89,6 +89,15 @@ class BenchmarkTest(TestBase):
         self.assertTrue(os.path.exists(benchmark.get_tex_file()))
         self.check_file_file(benchmark.get_tex_file(), "exreport_tex")
 
+    @staticmethod
+    def generate_excel_sheet(test, sheet, file_name):
+        with open(os.path.join("test_files", file_name), "w") as f:
+            for row in range(1, sheet.max_row + 1):
+                for col in range(1, sheet.max_column + 1):
+                    value = sheet.cell(row=row, column=col).value
+                    if value is not None:
+                        print(f'{row};{col};"{value}"', file=f)
+
     def test_excel_output(self):
         benchmark = Benchmark("accuracy", visualize=False)
         benchmark.compile_results()
@@ -101,6 +110,3 @@ class BenchmarkTest(TestBase):
         for sheet_name in book.sheetnames:
             sheet = book[sheet_name]
             self.check_excel_sheet(sheet, f"exreport_excel_{sheet_name}")
-            # ExcelTest.generate_excel_sheet(
-            #     self, sheet, f"exreport_excel_{sheet_name}"
-            # )

benchmark/tests/Util_test.py

@@ -179,6 +179,7 @@ class UtilTest(TestBase):
             "stratified": "0",
             "source_data": "Tanveer",
             "seeds": "[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]",
+            "discretize": "0",
         }
         computed = EnvData().load()
         self.assertDictEqual(computed, expected)

benchmark/tests/scripts/Be_Report_test.py

@@ -1,6 +1,6 @@
 import os
 from openpyxl import load_workbook
-from ...Utils import Folders
+from ...Utils import Folders, Files
 from ..TestBase import TestBase
 
 
@@ -43,6 +43,15 @@ class BeReportTest(TestBase):
         self.assertEqual(stderr.getvalue(), "")
         self.check_output_file(stdout, "report_datasets")
 
+    def test_be_report_datasets_excel(self):
+        stdout, stderr = self.execute_script("be_report", ["-x", "1"])
+        self.assertEqual(stderr.getvalue(), "")
+        self.check_output_file(stdout, "report_datasets")
+        file_name = os.path.join(os.getcwd(), Files.datasets_report_excel)
+        book = load_workbook(file_name)
+        sheet = book["Datasets"]
+        self.check_excel_sheet(sheet, "exreport_excel_datasets")
+
     def test_be_report_best(self):
         stdout, stderr = self.execute_script(
             "be_report", ["-s", "accuracy", "-m", "STree", "-b", "1"]

benchmark/tests/test_files/exreport_excel_Datasets.test

@@ -0,0 +1,25 @@
+1;1;"Datasets used in benchmark ver. 0.2.0"
+2;1;" Default score accuracy"
+2;2;"Cross validation"
+2;5;"5 Folds"
+3;2;"Stratified"
+3;5;"False"
+4;2;"Discretized"
+4;5;"False"
+5;2;"Seeds"
+5;5;"[57, 31, 1714, 17, 23, 79, 83, 97, 7, 1]"
+6;1;"Dataset"
+6;2;"Samples"
+6;3;"Features"
+6;4;"Classes"
+6;5;"Balance"
+7;1;"balance-scale"
+7;2;"625"
+7;3;"4"
+7;4;"3"
+7;5;" 7.84%/ 46.08%/ 46.08%"
+8;1;"balloons"
+8;2;"16"
+8;3;"4"
+8;4;"2"
+8;5;"56.25%/ 43.75%"

benchmark/tests/test_files/report_datasets.test

@@ -1,4 +1,6 @@
-Dataset                        Sampl. Feat. Cls Balance
+Datasets used in benchmark ver. 0.2.0
-============================== ===== ====== === ========================================
+
+Dataset                        Sampl. Feat. Cls Balance
+============================== ====== ===== === ============================================================
 balance-scale                     625     4   3  7.84%/ 46.08%/ 46.08%                  
 balloons                           16     4   2 56.25%/ 43.75%