some more fixes

setup.py

@@ -15,6 +15,7 @@
     long_description_content_type="text/markdown",
     url="https://github.com/harveycas/project_spring_2020",
     packages=setuptools.find_packages(),
+    install_requires = ['xlsxwriter'],
     classifiers=[
         "Programming Language :: Python :: 3",
         "License :: OSI Approved :: MIT License",

tests/test_tetrad_analysis.py

@@ -1,12 +1,12 @@
 import pytest
-from tetrad_analysis import dataframe_functions
+from tetrad_analysis import dataframe_functions as ddf
 import pandas as pd
 import numpy as np
 from pathlib import Path
 import os.path
 
 
-SAMPLE_XLSX = Path(__file__)/ "data"/"python_test_list.xlsx"
+SAMPLE_XLSX = Path(__file__).parent / "data"/"python_test_list.xlsx"
 SAMPLE_DF_TAIL = pd.DataFrame(
     data={
              "Plate": [1,1,1],
@@ -18,13 +18,13 @@
              "URA": [0,1,0],
              }
      )
-    
+COL = "URA"
 
 def test_read_excel_file():
 
     expected_tail = SAMPLE_DF_TAIL.set_index("Plate")
 
-    result = dataframe_functions.read_excel_file(SAMPLE_XLSX)
+    result = ddf.read_excel_file(SAMPLE_XLSX)
 
     assert result.tail(3) == expected_tail
 
@@ -33,15 +33,15 @@ def test_sort_and_filter_by_col():
 
     #For sorting input by col
 
-    expected_df = dataframe_functions.read_excel_file(SAMPLE_XLSX)
-    expected_df_sorted = dataframe_functions_in.sort_values([col], ascending = False)
+    expected_df = ddf.read_excel_file(SAMPLE_XLSX)
+    expected_df_sorted = expected_df.sort_values(["URA"], ascending = False)
 
     #test for isolating positive values:
 
-    expected_pos_vals = expected_df_sorted[expected_df_sorted[col]>0]
+    expected_pos_vals = expected_df_sorted[expected_df_sorted[COL]>0]
     expected_df_filtered = pd.DataFrame(expected_pos_vals)
 
-    result = dataframe_functions.sort_and_filter_by_col(expected_df,col)
+    result = ddf.sort_and_filter_by_col(expected_df,"URA")
 
     assert result == expected_df_filtered
 
@@ -53,15 +53,15 @@ def test_sort_and_filter_by_col():
 
 def test_combine_antibiotics():
 
-    expected_df = dataframe_functions.read_excel_file(SAMPLE_XLSX)
-
+    expected_df = ddf.read_excel_file(SAMPLE_XLSX)
+    markers = ['NAT','HYG','URA']
     expected_all_positive = {}
     for marker in markers:
-        expected_marker = dataframe_functions.sort_and_filter_by_col(marker)
+        expected_marker = ddf.sort_and_filter_by_col(expected_df,marker)
         expected_all_positive[marker + '_plus'] = expected_marker
     return expected_all_positive
 
-    result = dataframe_functions.test_combine_antibiotics(expected_df,markers)
+    result = ddf.test_combine_antibiotics(expected_df,markers)
 
     assert result == expected_all_positive
 
@@ -70,13 +70,16 @@ def test_combine_antibiotics():
 
 
 def test_write_marker_dict_to_disk():
-
+    file_out = "test.xlsx"
+    marker = "URA"
     writer = pd.ExcelWriter(file_out, engine='xlsxwriter')
-    for sheet_name in markers.keys():
-        markers[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
+
+    anti_bs = { "a": pd.DataFrame({ "Plate": [1,1,1], "Tetrad":[12,12,12],})}
+    for sheet_name in anti_bs.keys():
+        anti_bs[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
     expected_result = writer.save()
 
-    result = write_marker_dict_to_disk(marker,file_out)
+    result = ddf.write_marker_dict_to_disk(anti_bs,file_out)
 
     assert result == expected_result
 
@@ -85,14 +88,15 @@ def test_write_marker_dict_to_disk():
 
 
 def test_antibiotic_analysis():
+    file_out = "test.xlsx"
+    markers = ['NAT','HYG','URA']
+    expected_df = ddf.read_excel_file(SAMPLE_XLSX)
 
-    expected_df = dataframe_functions.read_excel_file(SAMPLE_XLSX)
-
-    expected_df_tetrad = read_excel_file(file_in)
-    expected_output_dict = combine_antibiotics(expected_df_tetrad, markers)
-    expected_result = writer_marker_dict_to_disk(expected_output_dict,file_out)
+    expected_df_tetrad = ddf.read_excel_file(SAMPLE_XLSX)
+    expected_output_dict = ddf.combine_antibiotics(expected_df_tetrad, markers)
+    expected_result = ddf.write_marker_dict_to_disk(expected_output_dict,file_out)
 
-    result = dataFrame_functions.test_antibiotic_analysis(file_in,file_out="Antibiotic_markers.xlsx",markers=['NAT','HYG','URA'])
+    result = ddf.antibiotic_analysis(SAMPLE_XLSX,file_out="Antibiotic_markers.xlsx",markers=markers)
 
     assert result == expected_result
 

tetrad_analysis/dataframe_functions.py

@@ -49,7 +49,7 @@ def combine_antibiotics(df_in,markers):
     #create one dataframe containing all of the positive markers
     all_positive = {}
     for marker in markers:
-        df_marker = sort_and_filter_by_col(marker)
+        df_marker = sort_and_filter_by_col(df_in,marker)
         all_positive[marker + '_plus'] = df_marker
 
     return all_positive
@@ -58,7 +58,7 @@ def combine_antibiotics(df_in,markers):
 
 
 
-def write_marker_dict_to_disk(marker,file_out):
+def write_marker_dict_to_disk(marker_dict,file_out):
     """
      Given a dict of dataframes, writes out an excel file in which each 
      dataframe occupies its own sheet
@@ -67,8 +67,8 @@ def write_marker_dict_to_disk(marker,file_out):
     #turn the dataframes stored in a dict into an excel document
     writer = pd.ExcelWriter(file_out, engine='xlsxwriter')
 
-    for sheet_name in markers.keys():
-        markers[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
+    for sheet_name in marker_dict.keys():
+        marker_dict[sheet_name].to_excel(writer, sheet_name=sheet_name, index=False)
 
     writer.save()