def test_read_csvs_zero_csv_path():
# Setup
# When no CSV files are on disk
# When reading files the functions raises ValueError.
try:
io.read_csvs("nofilesondisk.csv")
raise Exception
except ValueError:
pass
finally:
remove_csv_files()
def test_read_csvs_two_unmatching_csv_files():
# Setup
# When two csv files do not have same column names
df = pd.DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]],
columns=["a", "b", "c"])
df.to_csv(CSV_FILE_PATH.format(0), index=False)
df = pd.DataFrame([[1, 2, 3], [1, 2, 3], [1, 2, 3]],
columns=["d", "e", "f"])
df.to_csv(CSV_FILE_PATH.format(1), index=False)
# If the csv files are read into DataFrame
try:
io.read_csvs(CSV_FILE_PATH.format("*"))
# if read does read the unmatching files give an error
raise ValueError
except ValueError:
# If the read raises an exception it is ok
pass
finally:
remove_csv_files()
def test_read_csvs_three_csv_path():
# Setup
# When a CSV file with 3 cols and 3 rows is on disk
create_csv_file(3)
# If the csv file is read into DataFrame
dfs = io.read_csvs(CSV_FILE_PATH.format("*"))
# Then the dataframe has 3 cols and 9 rows
try:
assert len(dfs.columns) == 3
assert len(dfs) == 9
finally:
# Cleanup
remove_csv_files()
def test_read_csvs_three_csv_path():
# Setup
# When a CSV file with 3 cols and 4 rows is on disk
number_of_files = 3
create_csv_file(number_of_files)
# If the csv file is read into DataFrame
df = io.read_csvs(CSV_FILE_PATH.format("*"))
# Then the dataframe has 3 cols and 12 rows
try:
assert len(df.columns) == 3
assert len(df) == 4 * number_of_files
finally:
# Cleanup
remove_csv_files()
def test_read_csvs_three_separated_csv_path():
# Setup
# When a CSV file with 3 cols and 3 rows is on disk
create_csv_file(3)
# If the csv file is read into DataFrame
dfs = io.read_csvs(CSV_FILE_PATH.format("*"), seperate_df=True)
# Then the dataframe list has 3 dataframes
try:
assert len(dfs) == 3
for df in dfs.values():
assert len(df) == 3
assert len(df.columns) == 3
finally:
# Cleanup
remove_csv_files()
def test_read_csvs_three_separated_csv_path():
# Setup
# When a CSV file with 3 cols and 4 rows is on disk
number_of_files = 3
create_csv_file(number_of_files)
# If the csv file is read into DataFrame
dfs_dict = io.read_csvs(CSV_FILE_PATH.format("*"), separate_df=True)
# Then the dataframe list has 3 dataframes
try:
assert len(dfs_dict) == number_of_files
for df in dfs_dict.values(): # noqa: PD011
assert len(df) == 4
assert len(df.columns) == 3
finally:
# Cleanup
remove_csv_files()
def test_read_csvs_lists():
# Setup
# When a CSV file with 3 cols and 4 rows is on disk
number_of_files = 3
create_csv_file(number_of_files)
csvs_list = [CSV_FILE_PATH.format(i) for i in range(number_of_files)]
# If the list of csv files is read into DataFrame
dfs_list = io.read_csvs(files_path=csvs_list, separate_df=True)
# Then the dataframe list has 3 dataframes
try:
assert len(dfs_list) == number_of_files
for df in dfs_list.values(): # noqa: PD011
assert len(df) == 4
assert len(df.columns) == 3
finally:
# Cleanup
remove_csv_files()