Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
from sklearn.model_selection import train_test_split
|
4 |
+
from sklearn.naive_bayes import GaussianNB
|
5 |
+
from sklearn.metrics import accuracy_score
|
6 |
+
from sklearn.preprocessing import LabelEncoder
|
7 |
+
|
8 |
+
# Title of the app
|
9 |
+
st.title("Scoring Engine")
|
10 |
+
|
11 |
+
# File upload section
|
12 |
+
uploaded_file = st.file_uploader("Upload your dataset (CSV format)", type="csv")
|
13 |
+
|
14 |
+
if uploaded_file is not None:
|
15 |
+
# Load the dataset
|
16 |
+
df = pd.read_csv(uploaded_file)
|
17 |
+
|
18 |
+
st.write("### Uploaded Dataset")
|
19 |
+
st.write(df)
|
20 |
+
|
21 |
+
# Dynamically calculate the mean ignoring NaN values
|
22 |
+
df['Average_score'] = df[['Boss_score', 'Colleague_score', 'Colleague_other_score',
|
23 |
+
'Report_score', 'Customer_score', 'All_raters_Score']].mean(axis=1, skipna=True)
|
24 |
+
|
25 |
+
# Round the calculated average score to 2 decimal places
|
26 |
+
df['Average_score'] = df['Average_score'].round(1)
|
27 |
+
|
28 |
+
# Function to calculate self-score
|
29 |
+
def self_score(average, benchmark):
|
30 |
+
if average > benchmark:
|
31 |
+
return "High"
|
32 |
+
elif average < benchmark:
|
33 |
+
return "Low"
|
34 |
+
else:
|
35 |
+
return "Equal"
|
36 |
+
|
37 |
+
# Apply the function to calculate 'Self_score'
|
38 |
+
df['Self_score'] = df.apply(lambda row: self_score(row['Average_score'], row['Benchmark_score']), axis=1)
|
39 |
+
|
40 |
+
# Encode object-type columns
|
41 |
+
encoded_df = df.copy()
|
42 |
+
le = LabelEncoder()
|
43 |
+
for column in encoded_df.select_dtypes(include=['object']).columns:
|
44 |
+
encoded_df[column] = le.fit_transform(encoded_df[column].astype(str))
|
45 |
+
|
46 |
+
# Fill missing values with 0
|
47 |
+
encoded_df = encoded_df.fillna(0)
|
48 |
+
|
49 |
+
# Prepare features (X) and labels (y)
|
50 |
+
X = encoded_df.drop(columns=['Self_score'])
|
51 |
+
y = encoded_df['Self_score']
|
52 |
+
|
53 |
+
# Split data into training and testing sets
|
54 |
+
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.15, random_state=42)
|
55 |
+
|
56 |
+
# Train the Gaussian Naive Bayes model
|
57 |
+
gnb = GaussianNB()
|
58 |
+
gnb.fit(X_train, y_train)
|
59 |
+
|
60 |
+
# Make predictions and calculate confidence scores
|
61 |
+
y_pred = gnb.predict(X_test)
|
62 |
+
confidence_scores = gnb.predict_proba(X_test).max(axis=1)
|
63 |
+
|
64 |
+
# Evaluate the model
|
65 |
+
accuracy = accuracy_score(y_test, y_pred)
|
66 |
+
st.write(f"### Model Accuracy: {accuracy:.2f}")
|
67 |
+
|
68 |
+
# Predict confidence scores for the entire dataset
|
69 |
+
y_prob = gnb.predict_proba(X)
|
70 |
+
confidence_scores = y_prob.max(axis=1)
|
71 |
+
df['Confidence_score'] = confidence_scores
|
72 |
+
|
73 |
+
st.write("### Processed Dataset")
|
74 |
+
st.write(df)
|
75 |
+
|
76 |
+
# Download button for the processed dataset
|
77 |
+
csv = df.to_csv(index=False).encode('utf-8')
|
78 |
+
st.download_button(
|
79 |
+
label="Download Processed Dataset",
|
80 |
+
data=csv,
|
81 |
+
file_name="processed_dataset.csv",
|
82 |
+
mime="text/csv"
|
83 |
+
)
|
84 |
+
else:
|
85 |
+
st.write("Please upload a dataset to begin.")
|