def check_range(value, location, minValue):
if (value < minValue) or (value > maxValue):
prints.logerr(
"Value {0} in {1} is an integer out of the required range.".
format(value, location))
return True
return False
def isinstance_float(value, location, minValue):
if isinstance(value, float):
if value.is_integer():
tempInt = int(value)
return True, tempInt, check_range(value, location, minValue)
prints.logerr("Value {0} in {1} is not a required int.".format(
value, location))
return True, value, True
return False, value, False
def checkRange(dataSeries, rmin, rmax):
errRange = False
for value in dataSeries:
if (value < rmin) or (value > rmax):
prints.logerr(
'{0} outside of acceptable range for {1}. Accepted values are between {2} - {3}'
.format(value, dataSeries.name, rmin, rmax))
errRange = True
return errRange
def isinstance_obj(value, location, minValue):
try:
tempFloat = float(value)
except ValueError:
prints.logerr("{0} in {1} is not an integer.".format(
value, location))
return True, 0, True
isObj, value, intErrFlag = isinstance_float(tempFloat, location,
minValue)
return isObj, value, intErrFlag
def checkDup(dataSeries):
errDup = False
if dataSeries.duplicated().any():
errDup = True
sDuplicates = dataSeries[dataSeries.duplicated()]
for i in range(len(sDuplicates)):
prints.logerr("Duplicate {0} found '{1}'".format(
dataSeries.name,
dataSeries[dataSeries.duplicated()].iloc[i]))
return errDup
def checkExists(dataSeries):
errNan = False
for student in range(numStudents):
# Verify series has no NaN values
if pd.isna(dataSeries[student]) is True: # If element empty
prints.logerr(
"Empty element found in {0} column, row {1}".format(
dataSeries.name, student))
errNan = True
return errNan
def checkFloat(dataSeries):
errFloat = False
if is_numeric_dtype(dataSeries) is False:
errFloat = True
for student in range(numStudents):
try:
float(dataSeries[student])
except ValueError:
prints.logerr(
"Unexpected data found in {0}, row {1} = '{2}'".format(
dataSeries.name, student, dataSeries[student]))
return errFloat
def checkBool(dataSeries):
errBool = False
if is_bool_dtype(dataSeries) is False:
errBool = True
for student in range(numStudents):
val = dataSeries[student]
if val is not False:
val = val.lower()
if val is not False and val != 'true' and val != 'false':
prints.logerr(
"Unexpected data found in {0}, row {1} = '{2}'".format(
dataSeries.name, student, dataSeries[student]))
return errBool
def checkInt(dataSeries):
errInt = False
if is_numeric_dtype(dataSeries) is False: # Look at series label
errInt = True
for student in range(numStudents):
if dataSeries[student].isnumeric() is False and pd.isna(
dataSeries[student]) is False: # Look at element
prints.logerr(
"Unexpected data found in {0}, row {1} = '{2}'".format(
dataSeries.name, student, dataSeries[student]))
elif is_integer_dtype(dataSeries) is False:
for student in range(numStudents):
if not dataSeries[student].is_integer() and pd.isna(
dataSeries[student]) is False:
prints.logerr(
"Unexpected data found in {0}, row {1} = '{2}'".format(
dataSeries.name, student, dataSeries[student]))
return errInt
def csvFileCheck(csvFileName):
global errFlag
if not os.path.exists(csvFileName):
# if original filename not found, add .csv extension and check again
tempFileName = csvFileName + '.csv'
if not os.path.exists(tempFileName):
prints.logerr("{0} csv file can not be found.".format(csvFileName))
errFlag = True
return 0, 0
csvFileName = tempFileName
try:
tempDataStruct = pd.read_csv(csvFileName)
except ValueError:
prints.logerr("{0} is not a valid csv file.".format(csvFileName))
errFlag = True
return 0, 0
return tempDataStruct, csvFileName
def match1D(dataSeries,
parentData): # dataSeries is being checked against parentData
errMatch = False
for student in range(numStudents):
if pd.isna(dataSeries[student]) is False: # If element not empty
sMatch = False
for j in range(len(
parentData)): # Find matching element in parentData
if (dataSeries[student] == parentData[j]):
sMatch = True
# replace element with parentData index
dataSeries.at[student] = j
break
if sMatch is False:
prints.logerr(
"No match found in {0} column, row {1} = {2:n}".format(
dataSeries.name, student, dataSeries[student]))
errMatch = True
return errMatch
def matchProject2D(dataFrame):
errProj = False
# when Pandas finds unexpected data type, elements in dataFrame cast as objects, not int
for col in dataFrame.columns:
# Set flag for typecasting when column is not numeric
numeric = True
if is_numeric_dtype(dataFrame[col]) is False:
numeric = False
for row in dataFrame.index:
if pd.isna(
dataFrame[col][row]) is False: # If element not empty
# Numeric typecasting for when a letter is present in the column
if numeric is False:
try:
dataFrame.at[row, col] = int(dataFrame[col][row])
except:
prints.logerr(
"Unexpected data found in {0}, row {1} = '{2}'"
.format(col, row, dataFrame[col][row]))
errProj = True
for i in range(len(projectIDs)
): # Find matching id in global projectIDs
sChoiceMatch = False
if (dataFrame[col][row] == projectIDs[i]):
sChoiceMatch = True
# replace project id with project index
dataFrame.at[row, col] = i
break
if sChoiceMatch is False:
prints.logerr(
"No matching project id found for {0} = '{1}'".
format(col, dataFrame[col][row]))
errProj = True
return errProj
def projectsHandler(projectsFileData):
# arrays indexed by project
global minTeamSize
global maxTeamSize
global projectIDs
projectsErrFlag = False
# verify required project csv headers are present and not duplicated
requiredColumns = ['projectID', 'minTeamSize', 'maxTeamSize']
for col in requiredColumns:
if col not in projectsFileData.columns:
prints.err(
"Required {0} column not found in the projects csv file. Terminating Program."
.format(col))
else:
findDuplicateCols(projectsFileData, col, 'Projects CSV file')
# verify that all values in program csv file are integers
projectIDs, intErr = int_checker('projectID', None, projectsFileData, 1)
projectsErrFlag = check_error_flag(intErr, projectsErrFlag)
# verify that there are no duplicate project IDs in the projectID column
if projectsFileData.projectID.duplicated().any():
projectsErrFlag = True
projectDuplicates = projectsFileData[
projectsFileData.projectID.duplicated()]
for i in range(len(projectDuplicates)):
prints.logerr("Duplicate projectID found: {0}".format(
projectsFileData[
projectsFileData.projectID.duplicated()].iloc[i]))
# if values for team sizes are blank, enter size from settings csv and then verify all values are integers
projectsFileData['minTeamSize'] = projectsFileData['minTeamSize'].fillna(
defaultMinTeamSize)
minTeamSize, intErr = int_checker('minTeamSize', None, projectsFileData, 1)
projectsErrFlag = check_error_flag(intErr, projectsErrFlag)
projectsFileData['maxTeamSize'] = projectsFileData['maxTeamSize'].fillna(
defaultMaxTeamSize)
maxTeamSize, intErrFlag = int_checker('maxTeamSize', None,
projectsFileData, 1)
projectsErrFlag = check_error_flag(intErr, projectsErrFlag)
# verify minTeamSize is not greater than maxTeamSize
# zip() used to iterate in parallel over multiple iterables
for minSize, maxSize, pid in zip(minTeamSize, maxTeamSize, projectIDs):
if minSize > maxSize:
projectsErrFlag = True
prints.logerr(
"minTeamSize is greater than maxTeamSize for projectID {0}.".
format(pid))
# warn user if gap found in projectID sequence, assuming projectIDs start at projectID '1'
# arithmetic series = (n(firstNum + lastNum)) / 2, where n is # of terms in sequence,
# then subtract real sum of projectIDs
try:
projectIDGap = projectIDs[-1] * (projectIDs[0] +
projectIDs[-1]) / 2 - sum(projectIDs)
except ValueError:
projectIDGap = 0 # temp value to pass next if statement. Cause of error would have already been identified.
if not projectIDGap == 0:
prints.warn(
"gap found in projectID sequence in the projects csv file.")
return projectsErrFlag
def settingsHandler(settingsFileData):
global weightMaxLowGPAStudents
global weightMaxESLStudents
global weightMaxTeamSize
global weightMinTeamSize
global weightStudentPriority
global weightStudentChoice1
global weightAvoid
global effort
global maxLowGPAStudents
global maxESLStudents
global lowGPAThreshold
global defaultMaxTeamSize
global defaultMinTeamSize
settingsErrFlag = False
# verify required settings csv headers are present and not duplicated
requiredColumns = ['name', 'min', 'max', 'points']
for col in requiredColumns:
if col not in settingsFileData.columns:
prints.err(
"Required {0} column header not found in the settings csv. Terminating Program."
.format(col))
else:
findDuplicateCols(settingsFileData, col, 'Settings CSV file')
# verify required settings csv rows are present and not duplicated
requiredRows = [
'teamSize', 'lowGPAThreshold', 'maxLowGPAStudents', 'maxESLStudents',
'weightMaxLowGPAStudents', 'weightMaxESLStudents', 'weightMinTeamSize',
'weightMaxTeamSize', 'weightStudentPriority', 'weightStudentChoice1',
'weightAvoid', 'effort'
]
for row in requiredRows:
if row not in settingsFileData['name'].values:
prints.err(
"Required {0} row not found in the settings csv file. Terminating Program."
.format(row))
if len(settingsFileData[settingsFileData['name'] == row]) > 1:
prints.err(
"Required {0} row is duplicated in the settings csv file. Terminating Program."
.format(row))
# verify required fields in 'points' column contain integers
# if they are, assign value to global variable for scoring function to use
weightMaxLowGPAStudents, intErr = int_checker(
None, 'weightMaxLowGPAStudents',
(settingsFileData.set_index('name').at['weightMaxLowGPAStudents',
'points']), 0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightMaxESLStudents, intErr = int_checker(
None, 'weightMaxESLStudents',
(settingsFileData.set_index('name').at['weightMaxESLStudents',
'points']), 0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightMinTeamSize, intErr = int_checker(
None, 'weightMinTeamSize',
(settingsFileData.set_index('name').at['weightMinTeamSize', 'points']),
0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightMaxTeamSize, intErr = int_checker(
None, 'weightMaxTeamSize',
(settingsFileData.set_index('name').at['weightMaxTeamSize', 'points']),
0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightStudentPriority, intErr = int_checker(
None, 'weightStudentPriority',
(settingsFileData.set_index('name').at['weightStudentPriority',
'points']), 0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightStudentChoice1, intErr = int_checker(
None, 'weightStudentChoice1',
(settingsFileData.set_index('name').at['weightStudentChoice1',
'points']), 0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
weightAvoid, intErr = int_checker(
None, 'weightAvoid',
(settingsFileData.set_index('name').at['weightAvoid', 'points']), 0)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
# verify required values in 'max' and 'min' column are integers
# if they are, assign value to global variable for scoring function to use
defaultMaxTeamSize, intErr = int_checker(
None, 'teamSize',
(settingsFileData.set_index('name').at['teamSize', 'max']), 1)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
defaultMinTeamSize, intErr = int_checker(
None, 'teamSize',
(settingsFileData.set_index('name').at['teamSize', 'min']), 1)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
maxLowGPAStudents, intErr = int_checker(
None, 'maxLowGPAStudents',
(settingsFileData.set_index('name').at['maxLowGPAStudents', 'max']), 1)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
maxESLStudents, intErr = int_checker(
None, 'maxESLStudents',
(settingsFileData.set_index('name').at['maxESLStudents', 'max']), 1)
settingsErrFlag = check_error_flag(intErr, settingsErrFlag)
# if effort value is provided in the csv file, verify the value is an integer within the required range
# if it is not, use default value
try:
effort = int(settingsFileData.set_index('name').at['effort', 'max'])
except ValueError:
prints.warn(
"valid 'effort' value not found in the settings csv. Running with default value."
)
if effort < minEffort or effort > maxEffort:
effort = defaultEffort
prints.warn(
"'effort' in the settings csv is not an int between 1 and 100. Running with default value of 20."
)
# verify that provided lowGPAThreshold is not empty and that it's a float within range
# If it is, assign value to global variable for scoring function to use
try:
lowGPAThreshold = float(
settingsFileData.set_index('name').at['lowGPAThreshold', 'min'])
except ValueError:
prints.logerr("The lowGPAThreshold 'min' value is not a float.")
settingsErrFlag = True
lowGPAThreshold = 0 # temp value to pass statement below to allow program to continue checking for errors
if (lowGPAThreshold < minGPAThreshold) or (
lowGPAThreshold > maxGPAThreshold) or (pd.isna(lowGPAThreshold)):
prints.logerr(
"lowGPAThreshold 'min' setting requires a 0.00 - 4.00 value.")
settingsErrFlag = True
return settingsErrFlag