updating code to align with chapter

Author: cbrownley

csv/11csv_reader_select_contiguous_rows.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 import csv
-from string import strip
 import sys
 
 input_file = sys.argv[1]

csv/1csv_simple_parsing_and_write.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-from string import join, split, strip
 import sys
 
 input_file = sys.argv[1]

csv/3csv_reader_value_meets_condition.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 import csv
-from string import strip, replace
 import sys
 
 input_file = sys.argv[1]

csv/6csv_reader_column_by_index.py

@@ -7,8 +7,8 @@
 
 my_columns = [0, 3]
 
-with open(input_file, 'r') as csv_in_file:
-	with open(output_file, 'w') as csv_out_file:
+with open(input_file, 'r', newline='') as csv_in_file:
+	with open(output_file, 'w', newline='') as csv_out_file:
 		filereader = csv.reader(csv_in_file)
 		filewriter = csv.writer(csv_out_file)
 		for row_list in filereader:

csv/8csv_reader_counts_for_multiple_files.py

@@ -14,6 +14,7 @@
 		header = next(filereader)
 		for row in filereader:
 			row_counter += 1
-	print('{0!s}: \t{1:d} rows \t{2:d} columns'.format(os.path.basename(input_file), row_counter, len(header)))
+	print('{0!s}: \t{1:d} rows \t{2:d} columns'.format(\
+	os.path.basename(input_file), row_counter, len(header)))
 	file_counter += 1
 print('Number of files: {0:d}'.format(file_counter))

csv/pandas_add_header_row.py

@@ -5,7 +5,8 @@
 input_file = sys.argv[1]
 output_file = sys.argv[2]
 
-header_list = ['Supplier Name', 'Invoice Number', 'Part Number', 'Cost', 'Purchase Date']
+header_list = ['Supplier Name', 'Invoice Number', \
+'Part Number', 'Cost', 'Purchase Date']
 data_frame = pd.read_csv(input_file, header=None, names=header_list)
 
 data_frame.to_csv(output_file, index=False)

csv/pandas_column_by_index.py

@@ -6,6 +6,6 @@
 output_file = sys.argv[2]
 
 data_frame = pd.read_csv(input_file)
-data_frame_column_by_index = data_frame.ix[:, [0, 3]]
+data_frame_column_by_index = data_frame.iloc[:, [0, 3]]
 
 data_frame_column_by_index.to_csv(output_file, index=False)

csv/pandas_column_by_name.py

@@ -6,6 +6,6 @@
 output_file = sys.argv[2]
 
 data_frame = pd.read_csv(input_file)
-data_frame_column_by_name = data_frame.ix[:, ['Invoice Number', 'Purchase Date']]
+data_frame_column_by_name = data_frame.loc[:, ['Invoice Number', 'Purchase Date']]
 
 data_frame_column_by_name.to_csv(output_file, index=False)

csv/pandas_select_contiguous_rows.py

@@ -8,7 +8,7 @@
 data_frame = pd.read_csv(input_file, header=None)
 
 data_frame = data_frame.drop([0,1,2,16,17,18])
-data_frame.columns = data_frame.ix[3]
+data_frame.columns = data_frame.iloc[0]
 data_frame = data_frame.reindex(data_frame.index.drop(3))
 
-data_frame.to_csv(output_file, index=False)
+data_frame.to_csv(output_file, index=False)

csv/pandas_sum_average_from_multiple_files.py

@@ -12,17 +12,17 @@
 for input_file in all_files:
 	data_frame = pd.read_csv(input_file, index_col=None)
 
-	total_cost = pd.DataFrame([float(str(value).strip('$').replace(',','')) \
-						for value in data_frame.ix[:, 'Sale Amount']]).sum()
+	total_sales = pd.DataFrame([float(str(value).strip('$').replace(',','')) \
+						for value in data_frame.loc[:, 'Sale Amount']]).sum()
 
-	average_cost = pd.DataFrame([float(str(value).strip('$').replace(',','')) \
-						for value in data_frame.ix[:, 'Sale Amount']]).mean()
+	average_sales = pd.DataFrame([float(str(value).strip('$').replace(',','')) \
+						for value in data_frame.loc[:, 'Sale Amount']]).mean()
 
 	data = {'file_name': os.path.basename(input_file),
-			'total_cost': total_cost,
-			'average_cost': average_cost}
+			'total_sales': total_sales,
+			'average_sales': average_sales}
 
-	all_data_frames.append(pd.DataFrame(data, columns=['file_name', 'total_cost', 'average_cost']))
+	all_data_frames.append(pd.DataFrame(data, columns=['file_name', 'total_sales', 'average_sales']))
 
 data_frames_concat = pd.concat(all_data_frames, axis=0, ignore_index=True)