EdBoy2202 commited on
Commit
ef8a626
·
verified ·
1 Parent(s): bd96a0e

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +9 -7
app.py CHANGED
@@ -76,7 +76,8 @@ def predict_price(model, brand, model_name, year):
76
  'age': datetime.now().year - year,
77
  'age_squared': (datetime.now().year - year) ** 2,
78
  'mileage_per_year': 12000,
79
- 'model': model_name,
 
80
  'condition': 'Used',
81
  'fuel': 'Gasoline',
82
  'title_status': 'Clean',
@@ -149,15 +150,16 @@ if st.session_state.image is not None:
149
  st.write(f"Model: {classification['label']}")
150
  st.write(f"Confidence: {classification['score'] * 100:.2f}%")
151
 
152
- # Use the top prediction for further processing
153
  top_prediction = car_classifications[0]['label']
154
- brand, model_name = top_prediction.split(' ', 1)
155
 
156
- st.write(f"Identified Car: {brand} {model_name}")
 
157
 
158
  # Get additional information using GPT-3.5-turbo
159
  current_year = datetime.now().year
160
- overview = get_car_overview(brand, model_name, current_year)
161
  st.write("Car Overview:")
162
  st.write(overview)
163
 
@@ -170,13 +172,13 @@ if st.session_state.image is not None:
170
  predicted_prices = []
171
 
172
  for year in years:
173
- price = predict_price(model, brand, model_name, year)
174
  predicted_prices.append(price)
175
 
176
  # Plotting the results
177
  plt.figure(figsize=(10, 5))
178
  plt.plot(years, predicted_prices, marker='o')
179
- plt.title(f"Predicted Price of {brand} {model_name} Over Time")
180
  plt.xlabel("Year")
181
  plt.ylabel("Predicted Price ($)")
182
  plt.grid()
 
76
  'age': datetime.now().year - year,
77
  'age_squared': (datetime.now().year - year) ** 2,
78
  'mileage_per_year': 12000,
79
+ 'make': brand, # Use the separated make
80
+ 'model': model_name, # Use the separated model
81
  'condition': 'Used',
82
  'fuel': 'Gasoline',
83
  'title_status': 'Clean',
 
150
  st.write(f"Model: {classification['label']}")
151
  st.write(f"Confidence: {classification['score'] * 100:.2f}%")
152
 
153
+ # Separate make and model from the classification result
154
  top_prediction = car_classifications[0]['label']
155
+ make_name, model_name = top_prediction.split(' ', 1)
156
 
157
+ st.write(f"Identified Car Make: {make_name}")
158
+ st.write(f"Identified Car Model: {model_name}")
159
 
160
  # Get additional information using GPT-3.5-turbo
161
  current_year = datetime.now().year
162
+ overview = get_car_overview(make_name, model_name, current_year)
163
  st.write("Car Overview:")
164
  st.write(overview)
165
 
 
172
  predicted_prices = []
173
 
174
  for year in years:
175
+ price = predict_price(model, make_name, model_name, year)
176
  predicted_prices.append(price)
177
 
178
  # Plotting the results
179
  plt.figure(figsize=(10, 5))
180
  plt.plot(years, predicted_prices, marker='o')
181
+ plt.title(f"Predicted Price of {make_name} {model_name} Over Time")
182
  plt.xlabel("Year")
183
  plt.ylabel("Predicted Price ($)")
184
  plt.grid()