| import streamlit as st | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| st.title('Huayra app') | |
| df = pd.read_csv(r'CBT.csv') | |
| df1 = df.drop('UserID',axis=1) | |
| st.write("# <center><span style='font-size:24px'>Here is the DataFrame after cleaning</span></center>", unsafe_allow_html=True) | |
| st.dataframe(df1) | |
| st.image('xgboost log error.png') | |
| st.image('classfication auc.png') | |
| st.write("Higher AUC values indicate that the model performs better in distinguishing between positive and negative samples.") | |
| st.write("We get an AUC of **1** for the training set and **0.9985630707839712** for the test set. This indicates that the model performs very well.") | |
| st.image('precision recall curve.png') | |
| st.image('receiver operating character example.png') | |
| st.write("The P-R Curve (Precision-Recall Curve) is a curve used to evaluate the performance of a binary classification model, which shows the precision of the model under different recall rates.") | |
| st.write("Ideally, the P-R curve should be as close to the upper right as possible, which means that the model maintains a high precision at high recall.") | |
| st.image('predicted values.png') |