Delete Analyze-and-predict-student-scores

Analyze-and-predict-student-scores/All_maj.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d9b5865503b770f70fe93a3a1b39e2d53036b45a7fa5c5a17cf226cf9bf0545f
-size 47671628

Analyze-and-predict-student-scores/README.md

@@ -1,2 +0,0 @@
-# Analyze-and-predict-student-performance
-Link to web-app: https://itdsiu19001-analyze-and-predict-student-performance-main-oiibq6.streamlit.app/

Analyze-and-predict-student-scores/cols_to_drop.txt

@@ -1,13 +0,0 @@
-Intensive English 0- Twinning Program
-Intensive English 01- Twinning Program
-Intensive English 02- Twinning Program
-Intensive English 03- Twinning Program
-Intensive English 1- Twinning Program
-Intensive English 2- Twinning Program
-Intensive English 3- Twinning Program
-Listening & Speaking IE1
-Listening & Speaking IE2
-Listening & Speaking IE2 (for twinning program)
-Reading & Writing IE1
-Reading & Writing IE2
-Reading & Writing IE2 (for twinning program)

Analyze-and-predict-student-scores/column_all.txt

@@ -1,78 +0,0 @@
-Algorithms & Data Structures
-Analytics for Observational Data
-Applied Artificial Intelligence
-Basic Electrical Concepts & Circuits
-Blockchain
-C/C++ Programming
-C/C++ Programming in Unix
-Circuit Analysis
-Communication Networks
-Computer Architecture
-Computer Graphics
-Computer Networks
-Data Analysis
-Data Science and Data Visualization
-Decision Support System
-Digital Communications
-Digital Image Processing
-Digital Logic Design
-Digital Logic Design Laboratory
-Digital Signal Processing
-Discrete Mathematics
-Electronic Devices & Circuits
-Embedded Systems
-Entrepreneurship
-Formal Programming Methods
-Functional Programming
-Fundamental Concepts of Data Security
-Fundamentals of Big Data Technology
-Fundamentals of Programming
-Human-Computer Interaction
-IT Project Management
-Information System Management
-Information Theory & Coding
-Internet of Things
-Internship
-Introduction to Artificial Intelligence
-Introduction to Computing
-Introduction to Data Mining
-Introduction to Data Science
-Introduction to Distributed Computing
-Introduction to Wireless Network
-Linear Algebra
-Micro-processing Systems
-Microprocessor Systems & Interfacing
-Mobile Application Development
-Net-Centric Programming
-Network Design and Evaluation
-Network Management and Protocols
-Network Programming
-Networks & Systems Security
-Object Oriented Data Engineering (Java)
-Object-Oriented Analysis and Design
-Object-Oriented Programming
-Operating Systems
-Optimization
-Principles of Database Management
-Principles of EE1
-Principles of EE1 Laboratory
-Principles of Programming Languages
-Probability, Statistic & Random Process
-Programming Languages & Translators
-Projects
-Regression Analysis
-Scalable and Distributed Computing
-Signals & Systems
-Signals & Systems Laboratory
-Skills for Communicating Information
-Software Architecture
-Software Engineering
-Software Implementation
-Special Study of the Field
-Statistical Methods
-System & Network Administration
-System and Network Security
-Theoretical Models in Computing
-Thesis
-Web Application Development
-Web Programming

Analyze-and-predict-student-scores/config.toml

@@ -1,2 +0,0 @@
-[server]
-headless = true

Analyze-and-predict-student-scores/courses_list.txt

@@ -1,42 +0,0 @@
- Calculus 1
- Calculus 2
- Calculus 3
- Chemistry Laboratory
- Chemistry for Engineers
- Critical Thinking
- History of Vietnamese Communist Party
- Internship
- Philosophy of Marxism and Leninism
- Physics 1
- Physics 2
- Physics 3
- Physics 3 Laboratory
- Physics 4
- Political economics of Marxism and Leninism
- Principles of Database Management
- Principles of Marxism
- Principles of Programming Languages
- Probability, Statistic & Random Process
- Regression Analysis
- Revolutionary Lines of Vietnamese Communist Party
- Scientific socialism
- Speaking AE2
- Special Study of the Field
- Thesis
- Writing AE1
- Writing AE2
- Intensive English 0- Twinning Program
- Intensive English 01- Twinning Program
- Intensive English 02- Twinning Program
- Intensive English 03- Twinning Program
- Intensive English 1- Twinning Program
- Intensive English 2- Twinning Program
- Intensive English 3- Twinning Program
- Listening & Speaking IE1
- Listening & Speaking IE2
- Listening & Speaking IE2 (for twinning program)
- Physical Training 1
- Physical Training 2
- Reading & Writing IE1
- Reading & Writing IE2
- Reading & Writing IE2 (for twinning program)

Analyze-and-predict-student-scores/function.py

@@ -1,253 +0,0 @@
-import pandas as pd
-import numpy as np
-import plotly.express as px
-import plotly.graph_objs as go
-import streamlit as st
-import joblib
-
-
-def get_year(student_id):
-    return int(student_id[6:8])
-
-def process_data(raw_data):
-    # Pivot the DataFrame
-    pivot_df = pd.pivot_table(raw_data, values='DiemHP', index='MaSV', columns='TenMH', aggfunc='first')
-    pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
-    pivot_df.columns.name = None
-    pivot_df = pivot_df.dropna(thresh=50, axis=1)
-    pivot_df = pivot_df.rename(columns=lambda x: x.strip())
-    # Drop unnecessary columns
-    cols_to_drop = []
-    with open('cols_to_drop.txt', 'r') as f:
-      for line in f:
-        cols_to_drop.append(str(line.strip()))
-    existing_cols = [col for col in cols_to_drop if col in pivot_df.columns]
-    if existing_cols:
-        pivot_df.drop(existing_cols, axis=1, inplace=True)
-
-    # Merge with the XepLoaiNH column
-    df = pd.merge(pivot_df, raw_data[['MaSV', 'XepLoaiNH']], on='MaSV')
-    df.drop_duplicates(subset='MaSV', keep='last', inplace=True)
-    dfid=df['MaSV']
-    df.drop(['MaSV', 'XepLoaiNH'], axis=1, inplace=True)
-    df.replace(['WH', 'VT',"I"], np.nan, inplace=True)
-    df.iloc[:, :-1] = df.iloc[:, :-1].apply(pd.to_numeric)
-    df = pd.merge(dfid,df,left_index=True, right_index=True)
-    df['MaSV_school'] = df['MaSV'].str.slice(2, 4)
-    df['Major'] = df['MaSV'].str.slice(0, 2)
-    df["Year"] = 2000 + df["MaSV"].apply(get_year)
-    df["Year"]=df["Year"].astype(str)
-    df=df.drop(columns='MaSV')
-    
-    return df
-    
-def process_data_per(raw_data):
-    # Pivot the DataFrame
-    pivot_df = pd.pivot_table(raw_data, values='DiemHP', index='MaSV', columns='TenMH', aggfunc='first')
-    pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
-    pivot_df.columns.name = None
-    pivot_df = pivot_df.dropna(thresh=50, axis=1)
-    pivot_df = pivot_df.rename(columns=lambda x: x.strip())
-
-    # Drop unnecessary columns
-    cols_to_drop = []
-    with open('cols_to_drop.txt', 'r') as f:
-      for line in f:
-        cols_to_drop.append(str(line.strip()))
-    existing_cols = [col for col in cols_to_drop if col in pivot_df.columns]
-    if existing_cols:
-        pivot_df.drop(existing_cols, axis=1, inplace=True)
-    pivot_df.replace('WH', np.nan, inplace=True)
-    pivot_df.iloc[:, 1:] = pivot_df.iloc[:, 1:].apply(pd.to_numeric)
-    # Merge with the XepLoaiNH column
-    df = pd.merge(pivot_df, raw_data[['MaSV', 'XepLoaiNH']], on='MaSV')
-    df.drop_duplicates(subset='MaSV', keep='last', inplace=True)
-    df.drop(['XepLoaiNH'], axis=1, inplace=True)
-    
-    return df
-
-
-def process_predict_data(raw_data):
-    dtk = raw_data[["MaSV", "DTBTKH4"]].copy()
-    dtk.drop_duplicates(subset="MaSV", keep="last", inplace=True)
-
-    count_duplicates = raw_data.groupby(["MaSV", "MaMH"]).size().reset_index(name="Times")
-    courses = raw_data[raw_data['MaMH'].str.startswith('IT')]
-    courses_list=courses['MaMH'].unique().tolist()
-
-  # Create two new columns for counting courses that are in the courses_list or not
-    count_duplicates["fail_courses_list"] = (
-        (count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] >= 2)
-    ).astype(int)
-
-    count_duplicates["fail_not_courses_list"] = (
-        (~count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] >= 2)
-    ).astype(int)
-
-    count_duplicates["pass_courses"] = (
-        (~count_duplicates["MaMH"].isin(courses_list)) & (count_duplicates["Times"] == 1)
-    ).astype(int)
-
-    # Group the data by "MaSV" and sum the counts for the two new columns
-    fail = (
-        count_duplicates.groupby("MaSV")[["fail_courses_list", "fail_not_courses_list"]]
-        .sum()
-        .reset_index()
-    )
-
-    # Rename the columns to reflect the split of courses_list and not courses_list
-    fail.columns = ["MaSV", "fail_courses_list_count", "fail_not_courses_list_count"]
-
-    df = pd.merge(dtk, fail, on="MaSV")
-    df = df.rename(columns={"DTBTKH4": "GPA"})
-
-    data = raw_data[['MaSV','NHHK','SoTCDat']]
-    data = data.drop_duplicates()
-    data = data.groupby(['MaSV'])['SoTCDat'].median().reset_index(name='Mean_Cre').round(2)
-
-    df = pd.merge(df, data, on='MaSV')
-    df1=raw_data[['MaSV','MaMH','NHHK']]
-    courses_list = raw_data[(raw_data['MaMH'].str.startswith('EN')) & ~(raw_data['MaMH'].str.contains('EN007|EN008|EN011|EN012'))].MaMH.tolist()
-    filtered_df = df1[df1['MaMH'].isin(courses_list)]
-    nhhk_counts = filtered_df.groupby('MaSV')['NHHK'].nunique().reset_index(name='EPeriod')
-    df = pd.merge(df, nhhk_counts, on='MaSV', how='left').fillna(0)
-    df=df[['MaSV','GPA'	,'Mean_Cre',	'fail_courses_list_count'	,'fail_not_courses_list_count'	,'EPeriod']]
-    return df
-
-def predict_late_student(test_df):
-    # Load the pre-trained model
-    model=joblib.load("model/R_Late.joblib")
-    model1=joblib.load("model/R_Sem.joblib")
-    # Process the student data
-    test_dfed = process_predict_data(test_df)
-
-    # Save the student ID column
-    std_id = test_dfed.iloc[:, 0]
-
-    # Drop the student ID column
-    test_dfed = test_dfed.drop(test_dfed.columns[0], axis=1)
-
-    # Make predictions using the pre-trained model
-    prediction = model.predict(test_dfed)
-
-    # Add a new column to the student data indicating if the student is late
-    
-
-    prediction1 = model1.predict(test_dfed)
-
-    # Add a new column to the student data indicating if the student is late
-    test_dfed['Period'] = prediction1
-    test_dfed['Result'] = ['late' if p == 1 else 'not late' for p in prediction]
-
-    # Add the student ID column back to the beginning of the DataFrame
-    test_dfed.insert(0, 'MaSV', std_id)
-    
-    for index, row in test_dfed.iterrows():
-      if row['Period'] <= 9 and row['Result'] == 'late':
-        test_dfed.loc[index, 'Period'] = row['Period'] / 2
-        test_dfed.loc[index, 'Result'] = 'may late'
-      else:
-        test_dfed.loc[index, 'Period'] = row['Period'] / 2
-
-    return test_dfed
-def predict_rank(raw_data):
-    # Pivot the DataFrame
-    raw_data = raw_data[raw_data["MaSV"].str.startswith("IT")]
-    raw_data = raw_data[raw_data['MaMH'].str.startswith('IT')]
-    pivot_df = pd.pivot_table(
-        raw_data, values="DiemHP", index="MaSV", columns="TenMH", aggfunc="first"
-    )
-    pivot_df = pivot_df.reset_index().rename_axis(None, axis=1)
-    pivot_df.columns.name = None
-    pivot_df = pivot_df.dropna(thresh=50, axis=1)
-    pivot_df = pivot_df.rename(columns=lambda x: x.strip())
-
-    pivot_df.replace("WH", np.nan, inplace=True)
-    pivot_df.iloc[:, 1:] = pivot_df.iloc[:, 1:].apply(pd.to_numeric)
-
-    # Merge with the XepLoaiNH column
-    df = pd.merge(pivot_df, raw_data[["MaSV", "DTBTK"]], on="MaSV")
-    df.drop_duplicates(subset="MaSV", keep="last", inplace=True)
-    col=df.drop(['MaSV', 'DTBTK'], axis=1)
-    
-    columns_data = []
-    with open('column_all.txt', 'r') as f:
-      for line in f:
-        columns_data.append(str(line.strip()))
-    
-
-    r=df.drop(columns=['MaSV','DTBTK'])
-    merge=r.columns.tolist()
-    dup=pd.DataFrame(columns=columns_data)
-    df= pd.merge(dup, df, on=merge, how='outer')
-    for col in df.columns:
-          if df[col].isnull().values.any():
-            df[col].fillna(value=df["DTBTK"], inplace=True)
-    std_id = df['MaSV'].copy()
-    df=df.drop(['MaSV', 'DTBTK'], axis=1)
-    df.sort_index(axis=1, inplace=True)
-    model=joblib.load("model/R_rank.joblib")
-    prediction = model.predict(df)
-    df['Pred Rank'] = prediction
-    df.insert(0, 'MaSV', std_id)
-    df=df[['MaSV','Pred Rank']]
-    return df
-
-
-def predict_one_student(raw_data, student_id):
-    # Subset the DataFrame to relevant columns and rows
-      student = process_data_per(raw_data)
-      filtered_df = student[student["MaSV"] == student_id]
-      if len(filtered_df) > 0:
-        selected_row = filtered_df.iloc[0, 1:].dropna()
-        colname = filtered_df.dropna().columns.tolist()
-        values = selected_row.values.tolist()
-
-      # create a line chart using plotly
-        fig1 = go.Figure()
-        fig1.add_trace(go.Histogram(x=values, nbinsx=40, name=student_id,marker=dict(color='rgba(50, 100, 200, 0.7)')))
-
-        # set the chart title and axis labels
-        fig1.update_layout(
-            title="Histogram for student {}".format(student_id),
-            xaxis_title="Value",
-            yaxis_title="Frequency",
-            width=500
-        )
-
-        # create a bar chart using plotly express
-        data = raw_data[['MaSV', 'NHHK', 'TenMH', 'DiemHP']]
-        data['TenMH'] = data['TenMH'].str.lstrip()
-        data['NHHK'] = data['NHHK'].apply(lambda x: str(x)[:4] + ' S ' + str(x)[4:])
-        rows_to_drop = []
-        with open('rows_to_drop.txt', 'r') as f:
-            for line in f:
-                rows_to_drop.append(str(line.strip()))
-        data = data[~data['TenMH'].isin(rows_to_drop)]
-        student_data = data[data['MaSV'] == student_id][['NHHK', 'TenMH', 'DiemHP']]
-        student_data['DiemHP'] = pd.to_numeric(student_data['DiemHP'], errors='coerce')
-
-        fig2 = px.bar(student_data, x='TenMH', y='DiemHP', color='NHHK', title='Student Score vs. Course')
-        fig2.update_layout(
-            title="Student Score vs. Course",
-            xaxis_title=None,
-            yaxis_title="Score",
-        )
-        fig2.add_shape(
-            type="line",
-            x0=0,
-            y0=50,
-            x1=len(student_data['TenMH'])-1,
-            y1=50,
-            line=dict(color='red', width=3)
-        )
-
-        # display the charts using st.column
-        col1, col2 = st.columns(2)
-        with col1:
-            st.plotly_chart(fig1)
-
-        with col2:
-            st.plotly_chart(fig2)
-      else:
-        st.write("No data found for student {}".format(student_id))

Analyze-and-predict-student-scores/main.py

@@ -1,310 +0,0 @@
-import pandas as pd
-import streamlit as st
-import plotly.express as px
-import numpy as np
-import plotly.graph_objs as go
-from function import process_data,predict_late_student, predict_rank,predict_one_student
-from datetime import datetime
-from PIL import Image
-import base64
-from io import BytesIO
-
-
-df = pd.DataFrame()
-
-
-def color_cell(val):
-    if val == "not late":
-        color = "green"
-    elif val == "may late":
-        color = "yellow"
-    elif val == "late":
-        color = "red"
-    else:
-        color = "black"
-    return "color: %s" % color
-
-
-def get_year(student_id):
-    return int(student_id[6:8])
-
-
-def generate_comment(median):
-    if median < 30:
-        comment = f"The median score for {course} is quite low at {median}. Students may need to work harder to improve their performance."
-    elif median < 50:
-        comment = f"The median score for {course} is below average at {median}. Students should work on improving their understanding of the material."
-    elif median < 80:
-        comment = f"The median score for {course} is solid at {median}. Students are making good progress but could still work on improving their skills."
-    else:
-        comment = f"The median score for {course} is outstanding at {median}. Students are doing an excellent job in this course."
-    return comment
-
-favicon = 'R.png'
-
-st.set_page_config(
-page_title='Student System',
-page_icon=favicon,
-layout='wide',
-)
-currentYear = datetime.now().year
-im1 = Image.open("R.png")
-
-# get the image from the URL
-
-
-# create a three-column layout
-col1, col2 = st.columns([1, 3])
-
-# add a centered image to the first and third columns
-with col1:
-    st.image(im1, width=150)
-
-
-# add a centered title to the second column
-with col2:
-    st.title("Student Performance Prediction System")
-
-
-# Load the raw data
-# uploaded_file = st.file_uploader("Choose a score file", type=["xlsx", "csv"])
-
-# if uploaded_file is not None:
-#     file_contents = uploaded_file.read()
-#     file_ext = uploaded_file.name.split(".")[-1].lower()  # Get the file extension
-    
-#     if file_ext == "csv":
-#         df = pd.read_csv(BytesIO(file_contents))
-#     elif file_ext in ["xls", "xlsx"]:
-#         df = pd.read_excel(BytesIO(file_contents))
-#     else:
-#         st.error("Invalid file format. Please upload a CSV or Excel file.")
-
-# raw_data = df.copy()
-raw_data = pd.read_csv("All_major.csv")
-st.sidebar.title("Analysis Tool")
-
-option = ["Dashboard", "Predict"]
-# Add an expander to the sidebar
-tabs = st.sidebar.selectbox("Select an option", option)
-
-
-# draw histogram
-# Streamlit app
-if tabs == "Dashboard":
-#     try:
-
-        df = process_data(raw_data)
-        unique_values_major = df["Major"].unique()
-        major=st.selectbox("Select a major:", unique_values_major)
-        if major == "All":
-        # If so, display the entire DataFrame
-          filtered_df = df.copy()
-        else:
-        # Otherwise, filter the DataFrame based on the selected value
-          filtered_df = df[df["Major"] == major]
-          filtered_df  = filtered_df.dropna(axis=1, how="all")
-        
-        # Select course dropdown
-        df=filtered_df
-        unique_values = df["MaSV_school"].unique()
-        all_values = np.concatenate([["All"],unique_values ])
-        school = st.selectbox("Select a school:", all_values)
-        if school == "All":
-        # If so, display the entire DataFrame
-          filtered_df = df.copy()
-        else:
-        # Otherwise, filter the DataFrame based on the selected value
-          filtered_df = df[df["MaSV_school"] == school]
-          filtered_df  = filtered_df.dropna(axis=1, how="all")
-        
-        # Select course dropdown
-        df=filtered_df
-        unique_values_year = df["Year"].unique()
-        all_values_year = np.concatenate([["All"],unique_values_year ])
-        year = st.selectbox("Select a year:", all_values_year)
-
-        if year == "All":
-            # If so, display the entire DataFrame
-            filtered_df = df.copy()
-        else:
-            # Otherwise, filter the DataFrame based on the selected value
-            filtered_df = df[df["Year"] == year]
-            filtered_df = filtered_df.dropna(axis=1, how="all")
-        
-        
-        df=filtered_df
-        
-        options = df.columns[:-3]
-        course = st.selectbox("Select a course:", options)
-
-        # Filter the data for the selected course
-        course_data = df[course].dropna()
-        
-        # Calculate summary statistics for the course
-
-        
-        st.write(generate_comment(course_data.median()))
-        # Show summary statistics
-        
-        st.write("Course:", course, " of ", school," student" )
-
-
-        col1, col2,col3= st.columns(3)
-
-        with col1:
-            fig = go.Figure()
-            fig.add_trace(
-                go.Histogram(
-                    x=course_data, nbinsx=40, name="Histogram"
-                )
-            )
-            fig.update_layout(
-                title="Histogram of Scores for {}".format(course),
-                xaxis_title="Score",
-                yaxis_title="Count",
-                height=400,
-                width=400
-            )
-            st.plotly_chart(fig)
-
-        with col2:
-            fig = go.Figure()
-            fig.add_trace(
-                go.Box(
-                    y=course_data, name="Box plot"
-                )
-            )
-            fig.update_layout(
-                title="Box plot of Scores for {}".format(course),
-                yaxis_title="Score",
-                height=400,
-                width=400
-            )
-            st.plotly_chart(fig)
-        with col3:
-            raw_data['MaSV_school'] = raw_data['MaSV'].str.slice(2, 4)
-            if school == "All":
-        # If so, display the entire DataFrame
-                data = raw_data.copy()
-            else:
-        # Otherwise, filter the DataFrame based on the selected value
-                data = raw_data[raw_data["MaSV_school"] == school]
-            df1=data[['TenMH','NHHK','DiemHP']].copy()
-            df1['DiemHP'] = pd.to_numeric(df1['DiemHP'], errors='coerce')
-            df1['NHHK'] = df1['NHHK'].apply(lambda x: str(x)[:4] + ' S ' + str(x)[4:])
-            selected_TenMH = " " + course
-            filtered_df1 = df1[df1['TenMH'] == selected_TenMH]
-            mean_DiemHP = filtered_df1.groupby('NHHK')['DiemHP'].mean().round(1).reset_index(name='Mean')
-            # Create Plotly line graph
-            fig = px.line(mean_DiemHP, x='NHHK', y='Mean', title=f"Mean DiemHP for{selected_TenMH} thought period")
-            fig.update_layout(
-              height=400,
-              width=400)           
-            st.plotly_chart(fig)
-
-
-#     except:
-#         st.write("Add CSV to analysis")
-
-
-# predict student
-
-elif tabs == "Predict":
-    try:
-        raw_data = pd.read_csv("dataScore.csv")
-        predict = predict_late_student(raw_data)
-        rank = predict_rank(raw_data)
-
-        predict = pd.merge(predict, rank, on="MaSV")
-        rank_mapping = {
-            "Khá": "Good",
-            "Trung Bình Khá": "Average good",
-            "Giỏi": "Very good",
-            "Kém": "Very weak",
-            "Trung Bình": "Ordinary",
-            "Yếu": "Weak",
-            "Xuất Sắc": "Excellent",
-        }
-        predict["Pred Rank"].replace(rank_mapping, inplace=True)
-
-        # Filter students who have a Result value of "late"
-        df_late = predict
-
-        MaSV = st.text_input("Enter Student ID:")
-        if MaSV:
-            df_filtered = predict[predict["MaSV"] == MaSV]
-            styled_table = (
-                df_filtered[["MaSV", "GPA", "Mean_Cre", "Pred Rank", "Result", "Period"]]
-                .style.applymap(color_cell)
-                .format({"GPA": "{:.2f}", "Mean_Cre": "{:.1f}", "Period": "{:.1f}"})
-            )
-            
-            with st.container():
-                st.write(styled_table)
-                predict_one_student(raw_data,MaSV)
-        else:
-            df_late = predict
-            # df_late = predict[(predict['Pred Rank'] == 'Yếu') | (predict['Pred Rank'] == 'Kém')]
-            df_late["Year"] = 2000 + df_late["MaSV"].apply(get_year)
-            df_late = df_late[
-                (df_late["Year"] != currentYear - 1) & (df_late["Year"] != currentYear - 2)
-            ]
-            year = st.selectbox("Select Year", options=df_late["Year"].unique())
-            df_filtered = df_late[df_late["Year"] == year]
-            styled_table = (
-                df_filtered[["MaSV", "GPA", "Mean_Cre", "Pred Rank", "Result", "Period"]]
-                .style.applymap(color_cell)
-                .format({"GPA": "{:.2f}", "Mean_Cre": "{:.2f}", "Period": "{:.2f}"})
-            )
-            csv = df_filtered.to_csv(index=False)
-            b64 = base64.b64encode(csv.encode()).decode()
-            href = f'<a href="data:file/csv;base64,{b64}" download="Preidct data.csv">Download CSV</a>'
-            st.markdown(href, unsafe_allow_html=True)
-            fig1 = px.pie(
-                df_filtered,
-                names="Pred Rank",
-                title="Pred Rank",
-                color_discrete_sequence=px.colors.sequential.Mint,
-                height=400,
-                width=400,
-            )
-            fig2 = px.pie(
-                df_filtered,
-                names="Result",
-                title="Result",
-                color_discrete_sequence=px.colors.sequential.Peach,
-                height=400,
-                width=400,
-            )
-            fig1.update_layout(
-                title={
-                    "text": "Pred Rank",
-                    "y": 0.95,
-                    "x": 0.5,
-                    "xanchor": "center",
-                    "yanchor": "top",
-                }
-            )
-            fig2.update_layout(
-                title={
-                    "text": "Result",
-                    "y": 0.95,
-                    "x": 0.5,
-                    "xanchor": "center",
-                    "yanchor": "top",
-                }
-            )
-            st.dataframe(styled_table)
-            col1, col2 = st.columns([1, 1])
-            with col1:
-                st.plotly_chart(fig1)
-            with col2:
-                st.plotly_chart(fig2)
-
-            
-
-        # display the grid of pie charts using Streamlit
-
-    except:
-        st.write('Add CSV to analysis')

Analyze-and-predict-student-scores/model/R_Late.joblib

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d201e84514a400d73d79097b43fabf12cc96923e7abb1bc5c3be22bc5dea7445
-size 497289

Analyze-and-predict-student-scores/model/R_Sem.joblib

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:adfbee871506a3a7e6e3ca02d7bd205cceab50fdbec47878d01773ed59dd5e7c
-size 2638353

Analyze-and-predict-student-scores/model/R_rank.joblib

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:89b2a11b69b622db9e2401c735d0bb0b4a5f791269de30c9799a0817f619cd96
-size 205089

Analyze-and-predict-student-scores/requirements.txt

@@ -1,8 +0,0 @@
-numpy
-Cython==0.29.21
-scikit-learn
-pandas
-plotly
-scipy
-pyDOE
-openpyxl

Analyze-and-predict-student-scores/rows_to_drop.txt

@@ -1,15 +0,0 @@
- Intensive English 0- Twinning Program
- Intensive English 01- Twinning Program
- Intensive English 02- Twinning Program
- Intensive English 03- Twinning Program
- Intensive English 1- Twinning Program
- Intensive English 2- Twinning Program
- Intensive English 3- Twinning Program
- Listening & Speaking IE1
- Listening & Speaking IE2
- Listening & Speaking IE2 (for twinning program)
- Physical Training 1
- Physical Training 2
- Reading & Writing IE1
- Reading & Writing IE2
- Reading & Writing IE2 (for twinning program)