Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,59 +1,173 @@
|
|
1 |
-
import os
|
2 |
-
from groq import Groq
|
3 |
import streamlit as st
|
4 |
import pandas as pd
|
5 |
import plotly.express as px
|
|
|
|
|
6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
|
8 |
-
#
|
9 |
-
|
10 |
-
# Initialize the Groq client with the API key
|
11 |
-
client = Groq(api_key="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")
|
12 |
-
|
13 |
-
|
14 |
|
15 |
-
|
16 |
-
|
17 |
-
Interacts with Groq API to analyze results and provide suggestions.
|
18 |
-
Args:
|
19 |
-
results (dict): The results containing water, energy, and carbon footprints.
|
20 |
-
mode (str): Either 'single' or 'comparison' analysis mode.
|
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 |
if fiber_impact_data and transport_impact_data and washing_impact_data:
|
56 |
comparison_mode = st.sidebar.checkbox("Enable Comparison Mode")
|
|
|
57 |
if comparison_mode:
|
58 |
# Input for two assessments
|
59 |
col1, col2 = st.columns(2)
|
@@ -67,10 +181,13 @@ if fiber_impact_data and transport_impact_data and washing_impact_data:
|
|
67 |
water2, energy2, carbon2 = calculate_footprints(weight2, composition2, lifecycle2)
|
68 |
|
69 |
# Display numerical comparison
|
70 |
-
st.markdown(f"""
|
71 |
-
|
72 |
-
|
73 |
-
|
|
|
|
|
|
|
74 |
|
75 |
# Bar chart comparison
|
76 |
comparison_data = pd.DataFrame({
|
@@ -80,27 +197,26 @@ if fiber_impact_data and transport_impact_data and washing_impact_data:
|
|
80 |
})
|
81 |
fig = px.bar(
|
82 |
comparison_data.melt(id_vars="Footprint Type", var_name="Assessment", value_name="Value"),
|
83 |
-
x="Footprint Type",
|
|
|
|
|
|
|
84 |
)
|
85 |
st.plotly_chart(style_figure(fig))
|
86 |
-
|
87 |
-
# Use Groq to analyze comparative results
|
88 |
-
results = {"water1": water1, "energy1": energy1, "carbon1": carbon1,
|
89 |
-
"water2": water2, "energy2": energy2, "carbon2": carbon2}
|
90 |
-
suggestion = analyze_results_with_groq(results, mode="comparison")
|
91 |
-
st.markdown(f"<div class='highlight'><h3>Groq Analysis</h3><p>{suggestion}</p></div>", unsafe_allow_html=True)
|
92 |
-
|
93 |
else:
|
94 |
# Input for a single assessment
|
95 |
weight, composition, lifecycle = get_inputs("Single")
|
96 |
water, energy, carbon = calculate_footprints(weight, composition, lifecycle)
|
97 |
|
98 |
# Display results
|
99 |
-
st.markdown(f"""
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
|
|
|
|
|
|
104 |
|
105 |
# Bar chart for single assessment
|
106 |
result_data = pd.DataFrame({
|
@@ -110,10 +226,14 @@ if fiber_impact_data and transport_impact_data and washing_impact_data:
|
|
110 |
fig = px.bar(result_data, x="Footprint Type", y="Value", title="Single Assessment Footprint Breakdown")
|
111 |
st.plotly_chart(style_figure(fig))
|
112 |
|
113 |
-
#
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
|
|
|
|
|
|
|
|
118 |
else:
|
119 |
-
st.error("Failed to
|
|
|
|
|
|
|
1 |
import streamlit as st
|
2 |
import pandas as pd
|
3 |
import plotly.express as px
|
4 |
+
import os
|
5 |
+
from groq import Groq
|
6 |
|
7 |
+
# Add custom CSS for the app background and highlighted text
|
8 |
+
def add_background():
|
9 |
+
background_url = "https://huggingface.co/spaces/ZainMalik0925/GreenLensAI_LCA/resolve/main/BCK2.jpg"
|
10 |
+
css = f"""
|
11 |
+
<style>
|
12 |
+
.stApp {{
|
13 |
+
background-image: url("{background_url}");
|
14 |
+
background-size: cover;
|
15 |
+
background-position: center;
|
16 |
+
background-attachment: fixed;
|
17 |
+
}}
|
18 |
+
.highlight {{
|
19 |
+
background-color: rgba(27, 27, 27, 0.7); /* 70% opaque black */
|
20 |
+
padding: 10px;
|
21 |
+
border-radius: 5px;
|
22 |
+
margin-bottom: 15px;
|
23 |
+
color: white;
|
24 |
+
}}
|
25 |
+
</style>
|
26 |
+
"""
|
27 |
+
st.markdown(css, unsafe_allow_html=True)
|
28 |
|
29 |
+
# Set page configuration
|
30 |
+
st.set_page_config(page_title="GreenLens AI", layout="wide")
|
|
|
|
|
|
|
|
|
31 |
|
32 |
+
# Call the background function
|
33 |
+
add_background()
|
|
|
|
|
|
|
|
|
34 |
|
35 |
+
# App title and subtitle
|
36 |
+
st.markdown("<h1 style='text-align: center; color: white;'>GreenLens AI</h1>", unsafe_allow_html=True)
|
37 |
+
st.markdown(
|
38 |
"""
|
39 |
+
<p style='text-align: center; color: white; font-size: 18px;'>
|
40 |
+
A Comprehensive Tool for Assessing Water, Energy, and Carbon Footprints of Textile Products 🌍
|
41 |
+
</p>
|
42 |
+
""",
|
43 |
+
unsafe_allow_html=True,
|
44 |
+
)
|
45 |
+
|
46 |
+
# Dataset URL
|
47 |
+
DATASET_URL = "https://huggingface.co/spaces/ZainMalik0925/GreenLensAI_LCA/resolve/main/DataSet01.xlsx"
|
48 |
+
|
49 |
+
# Load dataset from Hugging Face Spaces
|
50 |
+
@st.cache_data
|
51 |
+
def process_dataset(url):
|
52 |
+
try:
|
53 |
+
excel_content = pd.ExcelFile(url)
|
54 |
+
fiber_data = pd.read_excel(excel_content, sheet_name="Fiber Impact Data")
|
55 |
+
transport_data = pd.read_excel(excel_content, sheet_name="Transport Impact Data")
|
56 |
+
washing_data = pd.read_excel(excel_content, sheet_name="Washing Data")
|
57 |
+
|
58 |
+
# Convert data to dictionaries for calculations
|
59 |
+
fiber_impact_data = fiber_data.set_index("Fiber Type")[["Water (L/kg)", "Energy (MJ/kg)", "Carbon (kg CO2e/kg)"]].to_dict(orient="index")
|
60 |
+
transport_impact_data = transport_data.set_index("Transport Mode")["CFP (kg CO2e/km)"].to_dict()
|
61 |
+
washing_impact_data = washing_data.set_index("Washing Temperature")[["Water (L/kg)", "Energy Use (MJ/wash)", "Carbon (kg CO2e/wash)", "Dryer CFP (kg CO2e/cycle)"]].to_dict(orient="index")
|
62 |
+
return fiber_impact_data, transport_impact_data, washing_impact_data
|
63 |
+
except Exception as e:
|
64 |
+
st.error(f"Error loading dataset: {e}")
|
65 |
+
return None, None, None
|
66 |
+
|
67 |
+
# Calculate footprints
|
68 |
+
def calculate_footprints(weight, composition, lifecycle_inputs):
|
69 |
+
water_fp, energy_fp, carbon_fp = 0, 0, 0
|
70 |
+
for fiber, percentage in composition.items():
|
71 |
+
if fiber in fiber_impact_data:
|
72 |
+
data = fiber_impact_data[fiber]
|
73 |
+
fraction = percentage / 100
|
74 |
+
water_fp += data["Water (L/kg)"] * weight * fraction
|
75 |
+
energy_fp += data["Energy (MJ/kg)"] * weight * fraction
|
76 |
+
carbon_fp += data["Carbon (kg CO2e/kg)"] * weight * fraction
|
77 |
+
|
78 |
+
# Add transport impact
|
79 |
+
if lifecycle_inputs["transport_mode"] in transport_impact_data:
|
80 |
+
carbon_fp += transport_impact_data[lifecycle_inputs["transport_mode"]] * lifecycle_inputs["transport_distance"] * weight
|
81 |
+
|
82 |
+
# Add washing impact
|
83 |
+
if lifecycle_inputs["washing_temperature"] in washing_impact_data:
|
84 |
+
washing_data = washing_impact_data[lifecycle_inputs["washing_temperature"]]
|
85 |
+
washing_water = washing_data["Water (L/kg)"] * lifecycle_inputs["washing_cycles"]
|
86 |
+
washing_energy = washing_data["Energy Use (MJ/wash)"] * lifecycle_inputs["washing_cycles"]
|
87 |
+
washing_carbon = washing_data["Carbon (kg CO2e/wash)"] * lifecycle_inputs["washing_cycles"]
|
88 |
+
dryer_carbon = washing_data["Dryer CFP (kg CO2e/cycle)"] if lifecycle_inputs["use_dryer"] else 0
|
89 |
+
water_fp += washing_water
|
90 |
+
energy_fp += washing_energy
|
91 |
+
carbon_fp += washing_carbon + (dryer_carbon * lifecycle_inputs["washing_cycles"])
|
92 |
+
|
93 |
+
# Convert water from liters to kiloliters
|
94 |
+
water_fp /= 1000
|
95 |
+
return water_fp, energy_fp, carbon_fp
|
96 |
+
|
97 |
+
# Sidebar inputs
|
98 |
+
def get_inputs(prefix):
|
99 |
+
weight = st.sidebar.number_input(f"{prefix} Product Weight (kg)", min_value=0.0, value=0.0, step=0.01, key=f"{prefix}_weight")
|
100 |
+
st.sidebar.markdown(f"<h3 style='color: white;'>{prefix} Material Composition (%)</h3>", unsafe_allow_html=True)
|
101 |
+
cotton = st.sidebar.number_input("Conventional Cotton (%)", 0, 100, 0, step=1, key=f"{prefix}_cotton")
|
102 |
+
polyester = st.sidebar.number_input("Polyester (%)", 0, 100, 0, step=1, key=f"{prefix}_polyester")
|
103 |
+
nylon = st.sidebar.number_input("Nylon 6 (%)", 0, 100, 0, step=1, key=f"{prefix}_nylon")
|
104 |
+
acrylic = st.sidebar.number_input("Acrylic (%)", 0, 100, 0, step=1, key=f"{prefix}_acrylic")
|
105 |
+
viscose = st.sidebar.number_input("Viscose (%)", 0, 100, 0, step=1, key=f"{prefix}_viscose")
|
106 |
+
|
107 |
+
if cotton + polyester + nylon + acrylic + viscose != 100:
|
108 |
+
st.sidebar.error("Fiber composition must sum to 100%!")
|
109 |
+
|
110 |
+
st.sidebar.markdown(f"<h3 style='color: white;'>{prefix} Transport Inputs</h3>", unsafe_allow_html=True)
|
111 |
+
transport_mode = st.sidebar.selectbox(f"{prefix} Transport Mode", list(transport_impact_data.keys()), key=f"{prefix}_transport_mode")
|
112 |
+
transport_distance = st.sidebar.number_input(f"{prefix} Transport Distance (km)", min_value=0, value=0, step=10, key=f"{prefix}_transport_distance")
|
113 |
+
|
114 |
+
lifecycle_inputs = {
|
115 |
+
"washing_cycles": st.sidebar.number_input(f"{prefix} Washing Cycles", min_value=0, value=0, key=f"{prefix}_wash_cycles"),
|
116 |
+
"washing_temperature": st.sidebar.selectbox(f"{prefix} Washing Temperature", list(washing_impact_data.keys()), key=f"{prefix}_wash_temp"),
|
117 |
+
"use_dryer": st.sidebar.checkbox(f"{prefix} Use Dryer?", key=f"{prefix}_use_dryer"),
|
118 |
+
"transport_mode": transport_mode,
|
119 |
+
"transport_distance": transport_distance,
|
120 |
+
}
|
121 |
+
|
122 |
+
composition = {
|
123 |
+
"Conventional Cotton": cotton,
|
124 |
+
"Polyester": polyester,
|
125 |
+
"Nylon 6": nylon,
|
126 |
+
"Acrylic": acrylic,
|
127 |
+
"Viscose": viscose,
|
128 |
+
}
|
129 |
+
return weight, composition, lifecycle_inputs
|
130 |
+
|
131 |
+
# Adjust graph styling
|
132 |
+
def style_figure(fig):
|
133 |
+
fig.update_layout(
|
134 |
+
plot_bgcolor="rgba(27, 27, 27, 0.8)", # 20% transparency
|
135 |
+
paper_bgcolor="rgba(27, 27, 27, 0.8)", # 20% transparency
|
136 |
+
font=dict(color="white"), # Font color set to white
|
137 |
+
title_font=dict(size=18, color="white"), # Title font white
|
138 |
+
xaxis=dict(title_font=dict(color="white"), tickfont=dict(color="white")),
|
139 |
+
yaxis=dict(title_font=dict(color="white"), tickfont=dict(color="white")),
|
140 |
)
|
141 |
+
fig.update_traces(marker=dict(color="white", line=dict(color="gray", width=1))) # Simulate 3D effect with border
|
142 |
+
return fig
|
143 |
+
|
144 |
+
# Generate recommendations using Groq API
|
145 |
+
def generate_recommendations(water, energy, carbon):
|
146 |
+
try:
|
147 |
+
client = Groq(api_key="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"
|
148 |
+
prompt = (
|
149 |
+
f"The environmental impact values for a textile product are as follows:\n"
|
150 |
+
f"Water Footprint: {water:.2f} kL\n"
|
151 |
+
f"Energy Footprint: {energy:.2f} MJ\n"
|
152 |
+
f"Carbon Footprint: {carbon:.2f} kg CO2e\n"
|
153 |
+
f"Provide recommendations to lower these impacts."
|
154 |
+
)
|
155 |
|
156 |
+
response = client.chat.completions.create(
|
157 |
+
messages=[{"role": "user", "content": prompt}],
|
158 |
+
model="llama-3.3-70b-versatile",
|
159 |
+
)
|
160 |
|
161 |
+
return response.choices[0].message.content
|
162 |
+
except Exception as e:
|
163 |
+
return f"Error generating recommendations: {e}"
|
164 |
|
165 |
+
# Main application logic
|
166 |
+
fiber_impact_data, transport_impact_data, washing_impact_data = process_dataset(DATASET_URL)
|
167 |
|
168 |
if fiber_impact_data and transport_impact_data and washing_impact_data:
|
169 |
comparison_mode = st.sidebar.checkbox("Enable Comparison Mode")
|
170 |
+
|
171 |
if comparison_mode:
|
172 |
# Input for two assessments
|
173 |
col1, col2 = st.columns(2)
|
|
|
181 |
water2, energy2, carbon2 = calculate_footprints(weight2, composition2, lifecycle2)
|
182 |
|
183 |
# Display numerical comparison
|
184 |
+
st.markdown(f"""
|
185 |
+
<div class="highlight">
|
186 |
+
<h2>Numerical Comparison</h2>
|
187 |
+
<p>Assessment 1: Water: {water1:.2f} kL, Energy: {energy1:.2f} MJ, Carbon: {carbon1:.2f} kg CO2e</p>
|
188 |
+
<p>Assessment 2: Water: {water2:.2f} kL, Energy: {energy2:.2f} MJ, Carbon: {carbon2:.2f} kg CO2e</p>
|
189 |
+
</div>
|
190 |
+
""", unsafe_allow_html=True)
|
191 |
|
192 |
# Bar chart comparison
|
193 |
comparison_data = pd.DataFrame({
|
|
|
197 |
})
|
198 |
fig = px.bar(
|
199 |
comparison_data.melt(id_vars="Footprint Type", var_name="Assessment", value_name="Value"),
|
200 |
+
x="Footprint Type",
|
201 |
+
y="Value",
|
202 |
+
color="Assessment",
|
203 |
+
title="Comparison of Assessments"
|
204 |
)
|
205 |
st.plotly_chart(style_figure(fig))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
else:
|
207 |
# Input for a single assessment
|
208 |
weight, composition, lifecycle = get_inputs("Single")
|
209 |
water, energy, carbon = calculate_footprints(weight, composition, lifecycle)
|
210 |
|
211 |
# Display results
|
212 |
+
st.markdown(f"""
|
213 |
+
<div class="highlight">
|
214 |
+
<h2>Single Assessment Results</h2>
|
215 |
+
<p>Water Footprint: {water:.2f} kL</p>
|
216 |
+
<p>Energy Footprint: {energy:.2f} MJ</p>
|
217 |
+
<p>Carbon Footprint: {carbon:.2f} kg CO2e</p>
|
218 |
+
</div>
|
219 |
+
""", unsafe_allow_html=True)
|
220 |
|
221 |
# Bar chart for single assessment
|
222 |
result_data = pd.DataFrame({
|
|
|
226 |
fig = px.bar(result_data, x="Footprint Type", y="Value", title="Single Assessment Footprint Breakdown")
|
227 |
st.plotly_chart(style_figure(fig))
|
228 |
|
229 |
+
# Generate recommendations if impact values are not zero
|
230 |
+
if water > 0 or energy > 0 or carbon > 0:
|
231 |
+
recommendations = generate_recommendations(water, energy, carbon)
|
232 |
+
st.markdown(f"""
|
233 |
+
<div class="highlight">
|
234 |
+
<h2>Recommendations to Lower Environmental Impacts</h2>
|
235 |
+
<p>{recommendations}</p>
|
236 |
+
</div>
|
237 |
+
""", unsafe_allow_html=True)
|
238 |
else:
|
239 |
+
st.error("Failed to load dataset.")
|