Spaces:
Sleeping
Sleeping
Commit
•
9184a71
1
Parent(s):
4d9329e
Update app.py
Browse files
app.py
CHANGED
@@ -2,7 +2,7 @@ from sklearn.preprocessing import OrdinalEncoder
|
|
2 |
import xgboost as xgb
|
3 |
import numpy as np
|
4 |
import matplotlib.pyplot as plt
|
5 |
-
import argparse, h5py, os, re
|
6 |
import streamlit as st
|
7 |
|
8 |
def get_POMFinder():
|
@@ -79,19 +79,17 @@ def POMPredicter(POMFinder, Gr, y_onehotenc_cat):
|
|
79 |
res = sorted(range(len(y_pred_proba)), key = lambda sub: y_pred_proba[sub]);
|
80 |
res.reverse();
|
81 |
st.markdown(f'<span style="font-size: 24px; color: green;">The 1st guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[0]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
82 |
-
|
83 |
-
st.
|
84 |
-
st.
|
85 |
-
st.
|
86 |
-
st.write("The 5th guess from the model is: ", str(y_onehotenc_cat.categories_[0][res[4]])[2:-2]+"cale.xyz")
|
87 |
|
88 |
return res, y_pred_proba
|
89 |
|
90 |
|
91 |
st.title('POMFinder')
|
92 |
-
|
93 |
-
st.write('
|
94 |
-
st.write('Upload a PDF to use DeepStruc to predict the structure.')
|
95 |
|
96 |
# Define the file upload widget
|
97 |
pdf_file = st.file_uploader("Upload PDF file in .gr format", type=["gr"])
|
@@ -100,7 +98,7 @@ pdf_file = st.file_uploader("Upload PDF file in .gr format", type=["gr"])
|
|
100 |
Qmin = st.number_input("Qmin value of the experimental PDF", min_value=0.0, max_value=2.0, value=0.7)
|
101 |
Qmax = st.number_input("Qmax value of the experimental PDF", min_value=15.0, max_value=40.0, value=30.0)
|
102 |
Qdamp = st.number_input("Qdamp value of the experimental PDF", min_value=0.00, max_value=0.08, value=0.04)
|
103 |
-
nyquist = st.checkbox("Is the data nyquist sampled", value=
|
104 |
|
105 |
parser = argparse.ArgumentParser(prog='POMFinder', formatter_class=argparse.ArgumentDefaultsHelpFormatter)
|
106 |
args = parser.parse_args()
|
@@ -129,10 +127,9 @@ else:
|
|
129 |
|
130 |
st.subheader('Cite')
|
131 |
|
132 |
-
st.write('If you use
|
133 |
|
134 |
-
st.write('
|
135 |
-
st.write('Characterising the atomic structure of mono-metallic nanoparticles from x-ray scattering data using conditional generative models **2020** (https://par.nsf.gov/biblio/10300745)')
|
136 |
|
137 |
st.subheader('LICENSE')
|
138 |
|
|
|
2 |
import xgboost as xgb
|
3 |
import numpy as np
|
4 |
import matplotlib.pyplot as plt
|
5 |
+
import argparse, h5py, os, re
|
6 |
import streamlit as st
|
7 |
|
8 |
def get_POMFinder():
|
|
|
79 |
res = sorted(range(len(y_pred_proba)), key = lambda sub: y_pred_proba[sub]);
|
80 |
res.reverse();
|
81 |
st.markdown(f'<span style="font-size: 24px; color: green;">The 1st guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[0]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
82 |
+
st.markdown(f'<span style="font-size: 24px; color: green;">The 2nd guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[1]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
83 |
+
st.markdown(f'<span style="font-size: 24px; color: green;">The 3rd guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[2]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
84 |
+
st.markdown(f'<span style="font-size: 24px; color: green;">The 4th guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[3]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
85 |
+
st.markdown(f'<span style="font-size: 24px; color: green;">The 5th guess from the model is: <b>{str(y_onehotenc_cat.categories_[0][res[4]])[2:-2]+"cale.xyz"}</b></span> <hr/>',unsafe_allow_html=True,)
|
|
|
86 |
|
87 |
return res, y_pred_proba
|
88 |
|
89 |
|
90 |
st.title('POMFinder')
|
91 |
+
st.write('Welcome to POMFinder which is a tree-based supervised learning algorithm that can predict the polyoxometalate cluster from a Pair Distribution Function.
|
92 |
+
st.write('Upload a PDF to use POMFinder to predict the structure.')
|
|
|
93 |
|
94 |
# Define the file upload widget
|
95 |
pdf_file = st.file_uploader("Upload PDF file in .gr format", type=["gr"])
|
|
|
98 |
Qmin = st.number_input("Qmin value of the experimental PDF", min_value=0.0, max_value=2.0, value=0.7)
|
99 |
Qmax = st.number_input("Qmax value of the experimental PDF", min_value=15.0, max_value=40.0, value=30.0)
|
100 |
Qdamp = st.number_input("Qdamp value of the experimental PDF", min_value=0.00, max_value=0.08, value=0.04)
|
101 |
+
nyquist = st.checkbox("Is the data nyquist sampled", value=False)
|
102 |
|
103 |
parser = argparse.ArgumentParser(prog='POMFinder', formatter_class=argparse.ArgumentDefaultsHelpFormatter)
|
104 |
args = parser.parse_args()
|
|
|
127 |
|
128 |
st.subheader('Cite')
|
129 |
|
130 |
+
st.write('If you use POMFinder, our code or results, please consider citing our paper. Thanks in advance!')
|
131 |
|
132 |
+
st.write('Title **2023** (Link)')
|
|
|
133 |
|
134 |
st.subheader('LICENSE')
|
135 |
|