ogegadavis254
commited on
Commit
•
bf0b824
1
Parent(s):
7fcff87
Update app.py
Browse files
app.py
CHANGED
@@ -3,7 +3,6 @@ import requests
|
|
3 |
import os
|
4 |
import json
|
5 |
import pandas as pd
|
6 |
-
import time
|
7 |
import matplotlib.pyplot as plt
|
8 |
|
9 |
# Function to call the Together AI model
|
@@ -35,10 +34,14 @@ def call_ai_model(all_message):
|
|
35 |
|
36 |
return response
|
37 |
|
38 |
-
# Function to request
|
39 |
-
def
|
40 |
all_message = (
|
41 |
-
f"Provide the expected
|
|
|
|
|
|
|
|
|
42 |
)
|
43 |
response = call_ai_model(all_message)
|
44 |
generated_text = ""
|
@@ -51,15 +54,20 @@ def get_numeric_performance_data(temperature):
|
|
51 |
json_data = json.loads(line_content)
|
52 |
if "choices" in json_data:
|
53 |
delta = json_data["choices"][0]["delta"]
|
54 |
-
if "content" in delta
|
55 |
-
|
56 |
except json.JSONDecodeError:
|
57 |
continue
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
# Streamlit app layout
|
61 |
-
st.title("Climate Impact on Sports Performance
|
62 |
-
st.write("Analyze and visualize the impact of climate conditions on sports performance
|
63 |
|
64 |
# Inputs for climate conditions
|
65 |
temperature = st.number_input("Temperature (°C):", min_value=-50, max_value=50, value=25)
|
@@ -70,70 +78,57 @@ air_quality_index = st.number_input("Air Quality Index:", min_value=0, max_value
|
|
70 |
precipitation = st.number_input("Precipitation (mm):", min_value=0.0, max_value=500.0, value=10.0)
|
71 |
atmospheric_pressure = st.number_input("Atmospheric Pressure (hPa):", min_value=900, max_value=1100, value=1013)
|
72 |
|
|
|
73 |
if st.button("Generate Prediction"):
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
|
|
|
|
|
|
|
|
79 |
|
80 |
try:
|
81 |
-
with st.spinner("
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
# Generate numeric performance data for different temperatures
|
121 |
-
temperatures = range(-10, 41, 5) # Temperatures from -10°C to 40°C in 5°C increments
|
122 |
-
performance_values = []
|
123 |
-
for temp in temperatures:
|
124 |
-
st.spinner(f"Fetching performance data for {temp}°C...")
|
125 |
-
performance_value = get_numeric_performance_data(temp)
|
126 |
-
if performance_value is not None:
|
127 |
-
performance_values.append(performance_value)
|
128 |
-
time.sleep(1)
|
129 |
-
|
130 |
-
if performance_values:
|
131 |
-
# Generate line graph
|
132 |
-
fig, ax = plt.subplots()
|
133 |
-
ax.plot(temperatures, performance_values, marker='o')
|
134 |
-
ax.set_xlabel('Temperature (°C)')
|
135 |
-
ax.set_ylabel('Performance Score')
|
136 |
-
ax.set_title('Temperature vs. Numeric Sports Performance')
|
137 |
st.pyplot(fig)
|
138 |
|
139 |
except ValueError as ve:
|
|
|
3 |
import os
|
4 |
import json
|
5 |
import pandas as pd
|
|
|
6 |
import matplotlib.pyplot as plt
|
7 |
|
8 |
# Function to call the Together AI model
|
|
|
34 |
|
35 |
return response
|
36 |
|
37 |
+
# Function to request performance data from AI
|
38 |
+
def get_performance_data(conditions):
|
39 |
all_message = (
|
40 |
+
f"Provide the expected sports performance score at conditions: "
|
41 |
+
f"Temperature {conditions['temperature']}°C, Humidity {conditions['humidity']}%, "
|
42 |
+
f"Wind Speed {conditions['wind_speed']} km/h, UV Index {conditions['uv_index']}, "
|
43 |
+
f"Air Quality Index {conditions['air_quality_index']}, Precipitation {conditions['precipitation']} mm, "
|
44 |
+
f"Atmospheric Pressure {conditions['atmospheric_pressure']} hPa."
|
45 |
)
|
46 |
response = call_ai_model(all_message)
|
47 |
generated_text = ""
|
|
|
54 |
json_data = json.loads(line_content)
|
55 |
if "choices" in json_data:
|
56 |
delta = json_data["choices"][0]["delta"]
|
57 |
+
if "content" in delta:
|
58 |
+
generated_text += delta["content"]
|
59 |
except json.JSONDecodeError:
|
60 |
continue
|
61 |
+
|
62 |
+
try:
|
63 |
+
return float(generated_text.strip())
|
64 |
+
except ValueError:
|
65 |
+
st.warning(f"Could not convert the response to a float: {generated_text}")
|
66 |
+
return None
|
67 |
|
68 |
# Streamlit app layout
|
69 |
+
st.title("Climate Impact on Sports Performance")
|
70 |
+
st.write("Analyze and visualize the impact of climate conditions on sports performance.")
|
71 |
|
72 |
# Inputs for climate conditions
|
73 |
temperature = st.number_input("Temperature (°C):", min_value=-50, max_value=50, value=25)
|
|
|
78 |
precipitation = st.number_input("Precipitation (mm):", min_value=0.0, max_value=500.0, value=10.0)
|
79 |
atmospheric_pressure = st.number_input("Atmospheric Pressure (hPa):", min_value=900, max_value=1100, value=1013)
|
80 |
|
81 |
+
# Button to generate predictions
|
82 |
if st.button("Generate Prediction"):
|
83 |
+
conditions = {
|
84 |
+
"temperature": temperature,
|
85 |
+
"humidity": humidity,
|
86 |
+
"wind_speed": wind_speed,
|
87 |
+
"uv_index": uv_index,
|
88 |
+
"air_quality_index": air_quality_index,
|
89 |
+
"precipitation": precipitation,
|
90 |
+
"atmospheric_pressure": atmospheric_pressure
|
91 |
+
}
|
92 |
|
93 |
try:
|
94 |
+
with st.spinner("Generating predictions..."):
|
95 |
+
# Call AI model to get initial prediction and qualitative assessment
|
96 |
+
response = call_ai_model(f"Assess the impact on sports performance at conditions: "
|
97 |
+
f"Temperature {temperature}°C, Humidity {humidity}%, "
|
98 |
+
f"Wind Speed {wind_speed} km/h, UV Index {uv_index}, "
|
99 |
+
f"Air Quality Index {air_quality_index}, Precipitation {precipitation} mm, "
|
100 |
+
f"Atmospheric Pressure {atmospheric_pressure} hPa.")
|
101 |
+
|
102 |
+
st.success("Initial analysis complete.")
|
103 |
+
|
104 |
+
# Get performance score for specified conditions
|
105 |
+
performance_score = get_performance_data(conditions)
|
106 |
+
if performance_score is not None:
|
107 |
+
st.success("Performance data fetched successfully.")
|
108 |
+
else:
|
109 |
+
st.warning("Failed to fetch performance data.")
|
110 |
+
|
111 |
+
# Plotting the data
|
112 |
+
if performance_score is not None:
|
113 |
+
# Prepare data for plotting
|
114 |
+
climate_conditions = list(conditions.keys())
|
115 |
+
climate_values = list(conditions.values())
|
116 |
+
|
117 |
+
fig, ax1 = plt.subplots()
|
118 |
+
|
119 |
+
# Plot climate conditions on the primary y-axis
|
120 |
+
ax1.plot(climate_conditions, climate_values, marker='o', color='b', label='Climate Conditions')
|
121 |
+
ax1.set_xlabel('Climate Conditions')
|
122 |
+
ax1.set_ylabel('Values', color='b')
|
123 |
+
ax1.tick_params(axis='y', labelcolor='b')
|
124 |
+
|
125 |
+
# Create a secondary y-axis for performance score
|
126 |
+
ax2 = ax1.twinx()
|
127 |
+
ax2.plot(['Performance Score'], [performance_score], marker='s', color='r', label='Performance Score')
|
128 |
+
ax2.set_ylabel('Performance Score', color='r')
|
129 |
+
ax2.tick_params(axis='y', labelcolor='r')
|
130 |
+
|
131 |
+
fig.tight_layout()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
st.pyplot(fig)
|
133 |
|
134 |
except ValueError as ve:
|