Spaces:
Paused
Paused
File size: 12,744 Bytes
e4fe207 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 |
# evaluation.py
import streamlit as st
import pandas as pd
from app5_selectbox.database_con import cursor, db_connection
from app5_selectbox.app5_selectbox_func import display_table, generate_unique_4
from app5_selectbox.evaluation_analysis import eval_analysis
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objs as go
# Function to perform analytics on instructors
def analyze_instructors(cursor):
try:
# Execute the SQL query to fetch the evaluation data
cursor.execute("SELECT * FROM evaluation")
evaluation_data = cursor.fetchall()
if not evaluation_data:
st.warning("No evaluation data found.")
else:
# Create a DataFrame from the fetched data and set column names
column_names = [i[0].replace("_", " ") for i in cursor.description]
df = pd.DataFrame(evaluation_data, columns=column_names)
# Get the column names for the score criteria
criteria_columns = [f"score_criteria_{i}" for i in range(10)]
column_names = [column[0].replace("_", " ") for column in cursor.description][4:14]
# Define criteria labels globally
criteria_labels = [(f"{column_names[i]}", f"{column_names[i]}".replace("_", " ")) for i in range(10)]
instructor_avg_scores = df.groupby("inst id")[column_names].mean().reset_index()
cursor.execute("SELECT inst_id, inst_name FROM instructor")
instructor_data = cursor.fetchall()
instructor_df = pd.DataFrame(instructor_data, columns=["inst id", "instructor name"])
instructor_avg_scores = instructor_avg_scores.merge(instructor_df, on="inst id", how="left")
selected_instructor = st.selectbox("Select Instructor", instructor_avg_scores["instructor name"].unique())
filtered_data = df[df["inst id"] == instructor_avg_scores[instructor_avg_scores["instructor name"] == selected_instructor]["inst id"].values[0]]
selected_instructor_comments = list(filtered_data["comments"])
st.subheader(f"Evaluated by: {len(selected_instructor_comments)} students")
cursor.execute("""
SELECT subj_inst.subj_inst_id, subject.sub_name
FROM subj_inst
INNER JOIN subject
ON subj_inst.sub_id_code = subject.sub_id_code
""")
subject_data = cursor.fetchall()
subject_df = pd.DataFrame(subject_data, columns=["subj inst id", "sub name"])
filtered_data = filtered_data.merge(subject_df, on="subj inst id", how="left")
subject_avg_scores = filtered_data.groupby("sub name")[column_names].mean().reset_index()
subject_avg_scores["total average"] = subject_avg_scores[column_names].mean(axis=1)
fig = go.Figure()
# for criterion, label in [("score_criteria_1", "Criteria 1"), ("score_criteria_2", "Criteria 2"), ("score_criteria_3", "Criteria 3")]:
# fig.add_trace(go.Bar(
# x=subject_avg_scores["sub_name"],
# y=subject_avg_scores[criterion],
# name=label,
# ))
criteria_labels = [(f"{column_names[i]}", f"{column_names[i]}".replace("_", " ")) for i in range(10)]
for criterion, label in criteria_labels:
fig.add_trace(go.Bar(
x=subject_avg_scores["sub name"],
y=subject_avg_scores[criterion],
name=label,
))
# Add the total average score above the bars
fig.add_trace(go.Scatter(
x=subject_avg_scores["sub name"],
y=subject_avg_scores["total average"],
mode="markers+text",
text=round(subject_avg_scores["total average"],2),
textposition="top center",
textfont=dict(size=14),
marker=dict(size=10, color="black"),
name="Total Average",
))
# Display the overall average of all subjects
overall_average = subject_avg_scores["total average"].mean()
# st.write(f"Overall Average Score (All Subjects): {overall_average:.2f}")
fig.update_layout(
barmode="group",
title=f"Average Scores per Criteria by Subject for Instructor: {selected_instructor}",
xaxis_title=f"Overall Average Score (All Subjects): {overall_average:.2f}",
yaxis_title="Average Score",
)
st.plotly_chart(fig)
# st.write("**Average score per Criteria**")
results_to_prompt = "Average score per Criteria\n"
criteria_averages = []
for criteria in filtered_data.columns[4:14]:
average_score = round(sum(filtered_data[criteria] / len(filtered_data)), 2)
criteria_averages.append((criteria, average_score))
results_to_prompt += f"{criteria}: {average_score}/5, \n"
# print(results_to_prompt)
# st.write(results_to_prompt)
# # Create a Plotly bar chart
fig = go.Figure()
fig.add_trace(go.Bar(
x=[criteria for criteria, _ in criteria_averages],
y=[score for _, score in criteria_averages],
text=[f"{score}/5" for _, score in criteria_averages],
# textposition='outside',
))
fig.update_layout(
title="Average Score per Criteria",
xaxis_title="Criteria",
yaxis_title="Average Score",
)
st.plotly_chart(fig)
for subject in subject_avg_scores["sub name"]:
subject_filtered_data = filtered_data[filtered_data["sub name"] == subject]
fig = go.Figure()
st.write(subject_filtered_data)
for criterion, label in criteria_labels:
fig.add_trace(go.Bar(
x=[label],
y=[subject_filtered_data[criterion].mean()],
text=[subject_filtered_data[criterion].mean()],
name=label,
))
# Calculate the "total average" based on criteria columns
total_average = subject_filtered_data[column_names].mean(axis=1).mean()
# # dot point for Total Average"
# fig.add_trace(go.Scatter(
# x=[label],
# y=[total_average],
# mode="markers+text",
# text=[round(total_average, 2)],
# textposition="top center",
# textfont=dict(size=14),
# marker=dict(size=10, color="black"),
# name="Total Average",
# ))
fig.update_layout(
barmode="group",
title=f"{subject} Average Score: {total_average:.2f}",
# xaxis_title=f"Overall Average Score: {total_average:.2f}",
yaxis_title="Average Score",
)
st.plotly_chart(fig)
# selected_instructor_comments.append(results_to_prompt)
# st.write(selected_instructor_comments)
return selected_instructor, selected_instructor_comments, results_to_prompt
except Exception as e:
st.error(f"An error occurred during data analytics: {str(e)}")
# try:
# # Execute the SQL query to fetch the evaluation data
# cursor.execute("SELECT * FROM evaluation")
# evaluation_data = cursor.fetchall()
# if not evaluation_data:
# st.warning("No evaluation data found.")
# else:
# # Create a DataFrame from the fetched data and set column names
# column_names = [i[0] for i in cursor.description]
# df = pd.DataFrame(evaluation_data, columns=column_names)
# # Group data by instructor and calculate average scores per criteria
# instructor_avg_scores = df.groupby("inst_id").agg({
# "score_criteria_1": "mean",
# "score_criteria_2": "mean",
# "score_criteria_3": "mean"
# }).reset_index()
# # Join with instructor data to get their names
# cursor.execute("SELECT inst_id, inst_name FROM instructor")
# instructor_data = cursor.fetchall()
# instructor_df = pd.DataFrame(instructor_data, columns=["inst_id", "instructor_name"])
# instructor_avg_scores = instructor_avg_scores.merge(instructor_df, on="inst_id", how="left")
# # Join with subj_inst and subject tables to get subject names
# cursor.execute("SELECT si.subj_inst_id, s.sub_name FROM subj_inst si INNER JOIN subject s ON si.sub_id_code = s.sub_id_code")
# subject_data = cursor.fetchall()
# subject_df = pd.DataFrame(subject_data, columns=["subj_inst_id", "sub_name"])
# df = df.merge(subject_df, on="subj_inst_id", how="left")
# # Create a select box to filter by instructor and subject
# selected_instructor = st.selectbox("Select Instructor", instructor_avg_scores["instructor_name"].unique())
# selected_subjects = df[df["inst_id"] == instructor_avg_scores[instructor_avg_scores["instructor_name"] == selected_instructor]["inst_id"].values[0]]["sub_name"].unique()
# selected_subject = st.selectbox("Select Subject", selected_subjects)
# # Filter data based on the selected instructor and subject
# filtered_data = df[(df["inst_id"] == instructor_avg_scores[instructor_avg_scores["instructor_name"] == selected_instructor]["inst_id"].values[0]) &
# (df["sub_name"] == selected_subject)]
# # Create a bar chart for average scores per criteria
# fig = px.bar(instructor_avg_scores, x="instructor_name",
# y=["score_criteria_1", "score_criteria_2", "score_criteria_3"],
# labels={"value": "Average Score", "variable": "Criteria"},
# title="Average Scores per Criteria by Instructor")
# st.plotly_chart(fig)
# # Group data by subject instructor and calculate average scores
# subject_avg_scores = filtered_data.groupby("sub_name").agg({
# "score_criteria_1": "mean",
# "score_criteria_2": "mean",
# "score_criteria_3": "mean"
# }).reset_index()
# # Create a bar chart for average scores per criteria for the selected subject
# fig = px.bar(subject_avg_scores, x="sub_name",
# y=["score_criteria_1", "score_criteria_2", "score_criteria_3"],
# labels={"value": "Average Score", "variable": "Criteria"},
# title=f"Average Scores per Criteria for Subject {selected_subject}")
# st.plotly_chart(fig)
# except Exception as e:
# st.error(f"An error occurred during data analytics: {str(e)}")
def evaluation(cursor, table_name):
try:
# Execute the SQL query to fetch the evaluation data
cursor.execute("SELECT * FROM evaluation")
evaluation_data = cursor.fetchall()
if not evaluation_data:
st.warning("No evaluation data found.")
else:
# Create a DataFrame from the fetched data and set column names
column_names = [i[0] for i in cursor.description]
df = pd.DataFrame(evaluation_data, columns=column_names)
# # Display the table with centered text
# st.header(f"{table_name} Table")
# st.dataframe(df.style.set_properties(**{'text-align': 'center'}))
analyze_instructors_results = analyze_instructors(cursor)
if st.button("Analyze comments"):
# st.write(analyze_instructors_results[0], analyze_instructors_results[1])
eval_analysis(analyze_instructors_results[0], analyze_instructors_results[1], analyze_instructors_results[2])
except Exception as e:
st.error(f"An error occurred while fetching evaluation data: {str(e)}")
|