def get_sample(column_name):
# This method will take input the type of the question from Data/Coded_Data/Headers.json
# This method will print Coded category, percentage of that category in data and all the responses under this category input 's' if you want to stop and enter to continue
question_file_name = get_question_from_header(
column_name).rstrip()[:-1].rstrip().replace(" ", "_") + "__1.csv"
dataframe, unique_codes = get_formatted_dataframe(question_file_name)
for item in unique_codes:
print('\033[31m', item, '\033[0m', sep='')
matching_rows = dataframe[getattr(dataframe, item) ==
True]['Answer'].index.to_list()
print('\033[31m',
"Percentage " +
str(round((len(matching_rows) / len(dataframe)) * 100, 2)) + "%",
'\033[0m',
sep='')
for element in matching_rows:
print(element + 1, dataframe.loc[element]['Answer'])
temp_input = input()
if temp_input == 's':
break
from CodeSample.SampleGenerator import get_formatted_dataframe
from FigureGenerators.ManagerExpectationFigure import ManagerExpectationFigureController
class ScalabilityFigureController(ManagerExpectationFigureController):
xlabel = "Percentage of Respondents(%)"
ylabel = ""
directory_name = "Scalability.eps"
figure_height = 20
figure_width = 10
y_tick_size = 30
if __name__ == "__main__":
column_name = "scalability"
question_file_name = get_question_from_header(
column_name).rstrip()[:-1].rstrip().replace(" ", "_") + "__1.csv"
dataframe, unique_codes = get_formatted_dataframe(question_file_name)
group = {
"Software Design": [
"Emphasizing on architecture",
"Efficient Design and Implementation", "Following design patterns"
],
"Database Design": ["Database optimization"],
"Software Testing": ["Load testing"],
"Framework/Platform/Tools": [
"Using Cloud Services", "Container Technology",
"Using SDK/framework"
]
}
controller = ScalabilityFigureController(dataframe)
controller.process_data(unique_codes=unique_codes,
def convert_column(column_name, question, dataframe):
file_name = question + "_raw_dataset.txt"
file = open(file_name, "w")
for item in dataframe.iterrows():
if USE_ZIP:
specifier = "\n==--endcodeableunit--==\n"
else:
specifier = "\n\n"
if isinstance(item[1][column_name], str):
file.write(item[1][column_name] + specifier)
else:
file.write("Did not responded. " + specifier)
file.close()
if __name__ == '__main__':
OPEN_ENDED_QUESTION_SET = [
'manager_expectation', 'RD_involvement', "scalability", "performance",
"security", "employee_expectation", "candidate_expectation",
"university_expectation", "government_expectation", "training"
]
# Load Data #
df = pd.read_csv("../Data/MainData.csv")
rename_header(df)
for item in OPEN_ENDED_QUESTION_SET:
question = get_question_from_header(item)
convert_column(item, question, df)
