def __init__(self, chat_df, students_df, filter_modes, time_delta,
start_sentence, zoom_names_to_ignore):
"""
:param chat_df: zoom chat (df)
:param students_df: student class raw data (df)
:param filter_modes: filters the user picked for parsing the text file (list of str)
:param time_delta: max time from start sentence to the last message to parse in each session in minutes (int)
:param start_sentence: start sentence that initiate sessions for parse (str)
:param zoom_names_to_ignore: zoom names that will not be considered (list of str)
:return: data frame with the data from the chat
"""
meta_data = AttendanceMetaData(
filter_modes=filter_modes,
time_delta=time_delta,
start_sentence=start_sentence,
zoom_names_to_ignore=zoom_names_to_ignore)
self.first_message_time = chat_df["time"].sort_values().iloc[
0] # get time of first message in the chat
start_indices = Attendance.get_start_indices(chat_df, meta_data)
df_students_for_report = students_df.set_index("id").astype(
str).reset_index() # set all columns to str except the id
self._df_students = df_students_for_report
self._sessions = []
for ind in range(len(start_indices)):
df_session = Attendance.get_df_of_time_segment(
chat_df, start_indices, ind, time_delta)
self._sessions.append(
Session(self._df_students, df_session, meta_data))
def test_get_start_indices(self, folders, student_df, chat_df_func,
filter_modes, file_name, time_delta,
start_sentence, zoom_names_to_ignore,
num_sessions):
chat_df = chat_df_func(os.path.join(folders["chat_folder"], file_name))
meta_data = AttendanceMetaData(
filter_modes=filter_modes,
time_delta=time_delta,
start_sentence=start_sentence,
zoom_names_to_ignore=zoom_names_to_ignore)
start_indices = Attendance.get_start_indices(chat_df, meta_data)
assert len(start_indices) == num_sessions
def test_get_relevant_chat_in_session(self, folders, chat_df_func, df_students_func, filter_modes,
chat_file_name, excel_file_name, time_delta, start_sentence, zoom_names_to_ignore, counting_dict):
chat_df = chat_df_func(os.path.join(folders["chat_files_folder"], chat_file_name))
student_df = df_students_func(os.path.join(folders["student_list_files_folder"], excel_file_name))
meta_data = AttendanceMetaData(filter_modes=filter_modes, time_delta=time_delta,
start_sentence=start_sentence, zoom_names_to_ignore=zoom_names_to_ignore)
start_indices = Attendance.get_start_indices(chat_df, meta_data)
df_students_for_report, report_df = Attendance.prepare_chat_and_classroom(student_df, chat_df)
for ind in range(len(start_indices)):
df_session = Attendance.get_df_of_time_segment(chat_df, start_indices, ind, time_delta)
session_part = Session.get_relevant_chat_in_session(df_students_for_report, df_session, meta_data)
assert session_part.shape[0] == counting_dict["total_messages"][ind]
assert (session_part["relevant"] == 1).sum() == counting_dict["relevant_messages"][ind]
def test_get_df_of_time_segment(self, folders, student_df, chat_df_func,
filter_modes, file_name, time_delta,
start_sentence, zoom_names_to_ignore,
list_rows_in_session):
chat_df = chat_df_func(os.path.join(folders["chat_folder"], file_name))
meta_data = AttendanceMetaData(
filter_modes=filter_modes,
time_delta=time_delta,
start_sentence=start_sentence,
zoom_names_to_ignore=zoom_names_to_ignore)
start_indices = Attendance.get_start_indices(chat_df, meta_data)
for ind in range(len(start_indices)):
df_session = Attendance.get_df_of_time_segment(
chat_df, start_indices, ind, time_delta)
assert df_session.shape[0] == list_rows_in_session[ind]
def test_first_message_time(self, folders, chat_df_func, df_students_func, filter_modes,
chat_file_name, excel_file_name, time_delta, start_sentence, zoom_names_to_ignore, message_time_tuples_list):
chat_df = chat_df_func(os.path.join(folders["chat_files_folder"], chat_file_name))
student_df = df_students_func(os.path.join(folders["student_list_files_folder"], excel_file_name))
meta_data = AttendanceMetaData(filter_modes=filter_modes, time_delta=time_delta,
start_sentence=start_sentence, zoom_names_to_ignore=zoom_names_to_ignore)
start_indices = Attendance.get_start_indices(chat_df, meta_data)
df_students_for_report = student_df.set_index("id").astype(str).reset_index()
for ind in range(len(start_indices)):
df_session = Attendance.get_df_of_time_segment(chat_df, start_indices, ind, time_delta)
current_session = Session(df_students_for_report, df_session, meta_data)
assert current_session._first_message_time.hour == message_time_tuples_list[ind][0]
assert current_session._first_message_time.minute == message_time_tuples_list[ind][1]
assert current_session._first_message_time.second == message_time_tuples_list[ind][2]
def __init__(self, chat_df, students_df, filter_modes, time_delta, start_sentence, zoom_names_to_ignore):
"""
:param chat_df: zoom chat (df)
:param students_df: student class raw data (df)
:param filter_modes: filters the user picked for parsing the text file (list of str)
:param time_delta: max time from start sentence to the last message to parse in each session in minutes (int)
:param start_sentence: start sentence that initiate sessions for parse (str)
:param zoom_names_to_ignore: zoom names that will not be considered (list of str)
:return: data frame with the data from the chat
"""
# create a nametuple for several values
meta_data = AttendanceMetaData(filter_modes=filter_modes, time_delta=time_delta,
start_sentence=start_sentence.lower(), zoom_names_to_ignore=zoom_names_to_ignore)
self.first_message_time = chat_df["time"].sort_values().iloc[0] # get time of first message in the chat
start_indices = Attendance.get_start_indices(chat_df, meta_data)
self._df_students, report_df = Attendance.prepare_chat_and_classroom(students_df, chat_df)
self._sessions = []
for ind in range(len(start_indices)):
df_session = Attendance.get_df_of_time_segment(report_df, start_indices, ind, time_delta)
self._sessions.append(Session(self._df_students, df_session, meta_data))