diff --git a/Adrien Payen_statistics.xlsx b/Adrien Payen_statistics.xlsx
deleted file mode 100644
index a1f752b154bcd6908d51748127d31b5f3f2a7121..0000000000000000000000000000000000000000
Binary files a/Adrien Payen_statistics.xlsx and /dev/null differ
diff --git a/Aubree Coleman_statistics.xlsx b/Aubree Coleman_statistics.xlsx
deleted file mode 100644
index 3fbcb6617a7cbfae85a41cbe295aa31ab8e7bc8e..0000000000000000000000000000000000000000
Binary files a/Aubree Coleman_statistics.xlsx and /dev/null differ
diff --git a/Cooper Lopez_statistics.xlsx b/Cooper Lopez_statistics.xlsx
deleted file mode 100644
index 720b644c99765c7763b608ac59a0cdbe19c4010b..0000000000000000000000000000000000000000
Binary files a/Cooper Lopez_statistics.xlsx and /dev/null differ
diff --git a/overall_statistics.xlsx b/overall_statistics.xlsx
deleted file mode 100644
index a1f752b154bcd6908d51748127d31b5f3f2a7121..0000000000000000000000000000000000000000
Binary files a/overall_statistics.xlsx and /dev/null differ
diff --git a/projet_personnel/algorithme_gestion_etudiants.py b/projet_personnel/algorithme_gestion_etudiants.py
index 693394b5111e4d11ab2d75e202dadf5ec194970f..d56573970741a4f89a4e4b40b9fec0386fce9f23 100644
--- a/projet_personnel/algorithme_gestion_etudiants.py
+++ b/projet_personnel/algorithme_gestion_etudiants.py
@@ -747,15 +747,11 @@ def see_the_data(data, columns_to_show=None):
# STATS
def statistics_analysis(data):
- print_menu([
- "Get basic statistics of a student",
- "Get all grades of a student",
- "Get all grades of a course",
- ])
-
+ print_menu(["Get basic statistics of a student", "Get all grades of a student", "Get all grades of a course"])
+
stats_choice = get_valid_input("Enter the number of what you want to do: ", 1, 3)
- if stats_choice == 1 :
+ if stats_choice == 1:
results = search_and_display_stats(data, "Statistics")
elif stats_choice == 2:
results = search_and_display_stats(data, "Grades")
@@ -797,13 +793,15 @@ def search_and_display_stats(data, stats_type):
if not results.empty:
if stats_type == "Statistics":
- display_statistics(results)
+ display_statistics(results, data)
elif stats_type == "Grades":
- display_student_grades(results)
+ display_student_grades(results, data)
else:
print(f"No students found with the specified {field_name}.")
-def display_statistics(results):
+
+# STATISTICAL_STUDENT
+def display_statistics(results, data):
numeric_columns = results.select_dtypes(include=['number']).columns
for index, row in results.iterrows():
@@ -812,11 +810,39 @@ def display_statistics(results):
if student_grades:
print_student_statistics(student_name, student_grades)
- else:
- print(f"\nNo grades found for student {student_name}.")
+
+ # Move the export_statistics call outside the loop
+ export_statistics(results, data, numeric_columns)
+
+
+def export_statistics(results, data, numeric_columns):
export_choice = input("Do you want to export these statistics? (YES/NO): ").upper()
if export_choice == 'YES':
- export_stats(results)
+ file_name = input("Enter the Excel file name (without extension): ") + '.xlsx'
+ export_path = file_name
+ export_df = calculate_student_stats(results, numeric_columns)
+ export_df.to_excel(export_path, index=False)
+ print(f"Statistics exported to {export_path}.")
+
+
+def calculate_student_stats(results, numeric_columns):
+ student_grades = pd.Series(results[numeric_columns].stack().dropna())
+
+ # Check if the student_grades Series is empty
+ if student_grades.empty:
+ # If no grades are found, return an empty DataFrame
+ return pd.DataFrame(columns=["Metric", "Value"])
+
+ student_stats = {
+ "Lowest grade": min(student_grades),
+ "Highest grade": max(student_grades),
+ "Average grade": statistics.mean(student_grades),
+ "Median grade": statistics.median(student_grades),
+ "Standard deviation of grades": statistics.stdev(student_grades)
+ }
+
+ return pd.DataFrame(list(student_stats.items()), columns=["Metric", "Value"])
+
def print_student_statistics(student_name, student_grades):
lowest_grade = min(student_grades)
@@ -836,16 +862,31 @@ def print_student_statistics(student_name, student_grades):
print(f"\nStatistics for student {student_name}:")
print(tabulate(table, headers=["Metric", "Value"], tablefmt="pretty"))
-def display_student_grades(results):
+# STUDENT_GRADES
+def display_student_grades(results, data):
for index, row in results.iterrows():
student_name = f"{row['Firstname']} {row['Lastname']}"
print(f"\nGrades for student {student_name}:")
table = [[column, grade] for column, grade in row.items() if pd.notna(grade) and column not in ['Firstname', 'Lastname', 'Academic Year', 'Curriculum', 'Place of Birth', 'Telephone', 'Address', 'Gender', 'Email', 'Campus', 'Date of Birth', 'Matricule']]
print(tabulate(table, headers=["Course", "Grade"], tablefmt="pretty"))
+ export_student_grades(results, data)
+
+def export_student_grades(results, data):
export_choice = input("Do you want to export these statistics? (YES/NO): ").upper()
if export_choice == 'YES':
- export_stats(results)
+ file_name = input("Enter the Excel file name (without extension): ") + '.xlsx'
+ export_path = file_name
+ columns_to_remove = ['Firstname', 'Lastname', 'Academic Year', 'Curriculum', 'Place of Birth', 'Telephone', 'Address', 'Gender', 'Email', 'Campus', 'Date of Birth', 'Matricule']
+ export_df = results.drop(columns=columns_to_remove)
+
+ # Melt the DataFrame to have data in columns with courses and grades
+ export_df_melted = pd.melt(export_df, id_vars=[], value_vars=export_df.columns, var_name='Course', value_name='Grade')
+
+ export_df_melted.to_excel(export_path, index=False)
+ print(f"Data exported to {export_path}.")
+
+# COURSE_GRADES
def course_grades(data):
print("Here is the list of courses:")
for course in data.columns[13:]:
@@ -857,53 +898,32 @@ def course_grades(data):
students_in_course = data[data[course_name].notnull()]
if not students_in_course.empty:
- display_course_grades(students_in_course, course_name)
+ display_course_grades(students_in_course, course_name, data)
+ export_course_grades(students_in_course, course_name)
else:
print(f"No students participated in the course {course_name}.")
else:
print(f"The specified course ({course_name}) was not found.")
-
- export_choice = input("Do you want to export these statistics? (YES/NO): ").upper()
- if export_choice == 'YES':
- export_stats(students_in_course)
-
- return students_in_course
+ return
-def display_course_grades(students_in_course, course_name):
+def display_course_grades(students_in_course, course_name, data):
print(f"\nGrades of students for the course {course_name}:")
- table = [
- ["Matricule", "Grade"],
- *[[row['Matricule'], row[course_name]] for _, row in students_in_course.iterrows() if not pd.isnull(row[course_name])]
+ table = [["Firstname", "Lastname", "Matricule", "Grade"],
+ *[[row['Firstname'], row['Lastname'], row['Matricule'], row[course_name]] for _, row in students_in_course.iterrows() if not pd.isnull(row[course_name])]
]
print(tabulate(table, headers="firstrow", tablefmt="pretty"))
-def export_stats(data):
- # Ensure numeric columns only
- numeric_columns = data.select_dtypes(include=['number']).columns
-
- # Calculate and save statistics for each student
- for index, row in data.iterrows():
- student_name = f"{row['Firstname']} {row['Lastname']}"
- student_stats = calculate_student_stats(row, numeric_columns)
- student_stats.to_excel(f"{student_name}_statistics.xlsx", index=False)
-
- print("Statistics exported successfully.")
-
-
+def export_course_grades(students_in_course, course_name):
+ export_choice = input("Do you want to export these statistics? (YES/NO): ").upper()
+ if export_choice == 'YES':
+ file_name = input("Enter the Excel file name (without extension): ") + '.xlsx'
+ export_path = file_name
+ export_df = students_in_course[['Firstname', 'Lastname','Matricule', course_name]]
+ export_df.to_excel(export_path, index=False)
+ print(f"Data exported to {export_path}.")
-def calculate_student_stats(row, numeric_columns):
- student_grades = [row[column] for column in numeric_columns if not pd.isnull(row[column])]
- student_stats = {
- "Lowest grade": min(student_grades),
- "Highest grade": max(student_grades),
- "Average grade": statistics.mean(student_grades),
- "Median grade": statistics.median(student_grades),
- "Standard deviation of grades": statistics.stdev(student_grades)
- }
-
- return pd.DataFrame(list(student_stats.items()), columns=["Metric", "Value"])
# Example of usage
diff --git a/~$adrien.xlsx b/~$adrien.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..d10daf560a7f8247050905285b3e618c244966d6
Binary files /dev/null and b/~$adrien.xlsx differ