File size: 2,347 Bytes
3c8d407 | 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 | import streamlit as st
import pandas as pd
import numpy as np
import pickle
# Load the k-means model from the pickle file
with open("kmeans_model.pkl", "rb") as f:
kmeans = pickle.load(f)
# Define a function to preprocess the uploaded data
def preprocess_data(data):
# Drop the Zone column since it is all NaN
data = data.drop(columns = "Zone")
# Drop the rows with missing ID
data = data.dropna(subset=['ID'])
# Fill the other missing values with mode
modes = data.mode().iloc[0]
data.fillna(modes, inplace=True)
# Select the relevant features
X = data.drop(columns = ["ID","At Risk Rate", "Disabled Rate", "Total Amount Post Upfront Amount", "Gender"])
# Convert categorical features to codes
cats = ["County", "Area", "Accounts Product Family"]
X[cats] = X[cats].apply(lambda x: pd.Categorical(x).codes)
# Apply log transformation to numerical features
conts = ["Age", "Repayment Speed", "Total Amount Paid"]
X[conts] = X[conts].apply(lambda x: np.log1p(x))
# Return the preprocessed data
return X
# Create a title for the app
st.title("Anomaly Detection on Repayment Speed")
# Create a sidebar for user input
st.sidebar.header("Upload your data")
# Allow the user to upload a file in csv or excel format
uploaded_file = st.sidebar.file_uploader("Choose a file", type=["csv", "xlsx"])
# If the user uploads a file, display it and make a prediction
if uploaded_file is not None:
# Read the uploaded file as a dataframe
if uploaded_file.type == "text/csv":
data = pd.read_csv(uploaded_file)
elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet":
data = pd.read_excel(uploaded_file)
data["ID"] = data["ID"].astype(str)
# Display the uploaded data
st.subheader("Your data")
st.write(data)
# Preprocess the data
X = preprocess_data(data)
# Make a prediction using the k-means model
prediction = kmeans.predict(X["Repayment Speed"].to_frame())
data_p = data.copy()
data_p = data_p.dropna(subset=['ID'])
data_p['Prediction'] = prediction
data_p['Prediction'] = data_p['Prediction'].replace({0: 'slower', 1: 'faster', 2: 'medium'})
data_p = data_p[["ID", "Prediction"]]
# Display the prediction
st.subheader("prediction")
st.write(data_p)
|