Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
import gradio as gr
|
2 |
import numpy as np
|
3 |
import pandas as pd
|
4 |
-
from sklearn.multioutput import MultiOutputRegressor
|
5 |
from sklearn.ensemble import GradientBoostingRegressor
|
6 |
import pickle
|
7 |
|
@@ -12,13 +11,13 @@ def create_gui():
|
|
12 |
# Define the input and output components of the GUI
|
13 |
inputs = [
|
14 |
gr.Dropdown(
|
15 |
-
["Benzocaine", "Ciprofloxacin", "Citalopram", "Diclofenac", "Dimetridazole", "Floxentine", "Ibuprofen", "Metronidazole", "Nitroimidazole", "Norfloxacin", "Oxytetracycline", "Salicylic Acid", "Sulfadiazine", "Sulfamethazine", "Sulfamethoxazole", "Tetracycline", "Triclosan"], label="Pharmaceutical
|
16 |
),
|
17 |
gr.Slider(minimum=0, maximum=950, step=0.01, label="TemP (K)"),
|
18 |
gr.Slider(minimum=0, maximum=480, step=0.01, label="Time (min)"),
|
19 |
gr.Slider(minimum=0, maximum=250, step=0.01, label="PS (mm)"),
|
20 |
-
gr.Slider(minimum=0, maximum=2000, step=0.01, label="BET (m2/g)"),
|
21 |
-
gr.Slider(minimum=0, maximum=1, step=0.01, label="
|
22 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="C (%)"),
|
23 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="H (%)"),
|
24 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="N (%)"),
|
@@ -26,21 +25,21 @@ def create_gui():
|
|
26 |
]
|
27 |
|
28 |
outputs = [
|
29 |
-
gr.Textbox(label="Qm (mg/g)")
|
30 |
]
|
31 |
|
32 |
# Define the title and description of the GUI
|
33 |
title = "GUI for Pharmaceutical Removal via Biochar Adsorption"
|
34 |
-
description = "This GUI uses machine learning to predict
|
35 |
|
36 |
-
gr.Interface(fn=
|
37 |
|
38 |
-
def
|
39 |
"""
|
40 |
-
Predicts
|
41 |
|
42 |
Parameters:
|
43 |
-
|
44 |
TemP (float): Temperature K of the biomass.
|
45 |
Time (float): Time it takes for biochar to remove pharmaceutical in minutes .
|
46 |
PS (float): Pore space in mm.
|
@@ -52,32 +51,21 @@ def biomass_prediction(pharm_type, temp, time, ps, bet, pv, c, h, n, o):
|
|
52 |
O (float): O (%) content of the biomass.
|
53 |
|
54 |
Returns:
|
55 |
-
float:
|
56 |
"""
|
57 |
|
58 |
# Concatenate the inputs into a numpy array
|
59 |
-
input_data = pd.DataFrame([[
|
60 |
-
columns=['pharm type', 'TemP (K)', 'Time (min)', 'PS (mm)', 'BET (m2/g)', 'PV (cm3)', 'C (%)', 'H (%)', 'N (%)', 'O (%)'])
|
61 |
-
|
62 |
-
# Check if values are zero or negative
|
63 |
-
if np.all(input_data <= 0):
|
64 |
-
return 0
|
65 |
|
66 |
# Load the trained model from the pickled file
|
67 |
-
|
68 |
-
with open('xgb_best_params.pkl', 'rb') as file:
|
69 |
loaded_model = pickle.load(file)
|
70 |
-
|
71 |
-
return "Model file not found"
|
72 |
# Make predictions using the loaded machine learning model
|
73 |
prediction = loaded_model.predict(input_data)
|
74 |
-
|
75 |
|
76 |
-
|
77 |
-
output1 = prediction[0][0]
|
78 |
-
|
79 |
-
# Return predicted output values
|
80 |
-
return output1
|
81 |
|
82 |
if __name__ == '__main__':
|
83 |
# Create GUI
|
|
|
1 |
import gradio as gr
|
2 |
import numpy as np
|
3 |
import pandas as pd
|
|
|
4 |
from sklearn.ensemble import GradientBoostingRegressor
|
5 |
import pickle
|
6 |
|
|
|
11 |
# Define the input and output components of the GUI
|
12 |
inputs = [
|
13 |
gr.Dropdown(
|
14 |
+
["Benzocaine", "Ciprofloxacin", "Citalopram", "Diclofenac", "Dimetridazole", "Floxentine", "Ibuprofen", "Metronidazole", "Nitroimidazole", "Norfloxacin", "Oxytetracycline", "Salicylic Acid", "Sulfadiazine", "Sulfamethazine", "Sulfamethoxazole", "Tetracycline", "Triclosan"], label="Select Pharmaceutical"
|
15 |
),
|
16 |
gr.Slider(minimum=0, maximum=950, step=0.01, label="TemP (K)"),
|
17 |
gr.Slider(minimum=0, maximum=480, step=0.01, label="Time (min)"),
|
18 |
gr.Slider(minimum=0, maximum=250, step=0.01, label="PS (mm)"),
|
19 |
+
gr.Slider(minimum=0, maximum=2000, step=0.01, label="BET surface area (m2/g)"),
|
20 |
+
gr.Slider(minimum=0, maximum=1, step=0.01, label="Pore Volume (cm3)"),
|
21 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="C (%)"),
|
22 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="H (%)"),
|
23 |
gr.Slider(minimum=0, maximum=100, step=0.01, label="N (%)"),
|
|
|
25 |
]
|
26 |
|
27 |
outputs = [
|
28 |
+
gr.Textbox(label="Predicted Maximum Adsorption Capacity, Qm (mg/g)")
|
29 |
]
|
30 |
|
31 |
# Define the title and description of the GUI
|
32 |
title = "GUI for Pharmaceutical Removal via Biochar Adsorption"
|
33 |
+
description = "This GUI uses machine learning to predict maximum absorption capacity (Qm) for the selected pharmaceutical based on various input parameters."
|
34 |
|
35 |
+
gr.Interface(fn=predict_qm, inputs=inputs, outputs=outputs, title=title, description=description).launch()
|
36 |
|
37 |
+
def predict_qm(pharmaceutical, temp, time, ps, bet, pv, c, h, n, o):
|
38 |
"""
|
39 |
+
Predicts maximum adsorption capacity (Qm) based on input features for the selected pharmaceutical.
|
40 |
|
41 |
Parameters:
|
42 |
+
pharmaceutical (str): Pharmaceutical type.
|
43 |
TemP (float): Temperature K of the biomass.
|
44 |
Time (float): Time it takes for biochar to remove pharmaceutical in minutes .
|
45 |
PS (float): Pore space in mm.
|
|
|
51 |
O (float): O (%) content of the biomass.
|
52 |
|
53 |
Returns:
|
54 |
+
float: The predicted maximum adsorption capacity (Qm).
|
55 |
"""
|
56 |
|
57 |
# Concatenate the inputs into a numpy array
|
58 |
+
input_data = pd.DataFrame([[temp, time, ps, bet, pv, c, h, n, o]], columns=["Temp", "Time", "PS", "BET", "PV", "C", "H", "N", "O"])
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
# Load the trained model from the pickled file
|
61 |
+
with open('xgb_best_params.pkl', 'rb') as file:
|
|
|
62 |
loaded_model = pickle.load(file)
|
63 |
+
|
|
|
64 |
# Make predictions using the loaded machine learning model
|
65 |
prediction = loaded_model.predict(input_data)
|
66 |
+
qm = np.round(prediction[0], 2)
|
67 |
|
68 |
+
return qm
|
|
|
|
|
|
|
|
|
69 |
|
70 |
if __name__ == '__main__':
|
71 |
# Create GUI
|