Update app.py

app.py

@@ -1,196 +1,196 @@
-import streamlit as st
-import joblib
-import pandas as pd
-from scipy.stats import yeojohnson
-import inv_transform
-import math
-
-
-
-# Title of the app
-st.title("Event Budget Estimate")
-
-# Add custom CSS for spacing between columns
-st.markdown(
-    """
-    <style>
-    .stColumn > div {
-        padding: 10px; /* Adjust the value as needed to increase spacing */
-    }
-    h2 {
-        font-size: 20px;
-    }
-    </style>
-    """, unsafe_allow_html=True)
-
-# Create columns with adjusted spacing
-col1, col2 = st.columns([1, 1], gap="large")  # Adjust gap as needed
-
-with col1:
-    # Smaller column title
-    #st.subheader("Event Data")
-    st.markdown("### Event Data")
-    
-    countries = pd.read_csv('ISO-3166-Countries-with-Regional-Codes.csv')
-    countries_a2 = list (countries['alpha-2'])
-    countries_names = list (countries['name'])
-    countries = [f"{a2} - {name}" for a2, name in zip(countries_a2, countries_names)]
-        
-    us_index = countries_a2.index('US')
-    #cn_index = countries_a2.index('CN')
-    in_index = countries_a2.index('IN')
-    
-    states = pd.read_csv('USA States.csv', index_col=0)
-    states = list(states.Abbreviation)
-    ca_index = states.index('CA')
-    
-    # Input fields
-    atnd_num = st.number_input("Estimate Number of Attendees", min_value=0, value=180)
-    ppr_num = st.number_input("Estimate Paper Number", min_value=0, value=100)
-    exh_num = st.number_input("Estimate Number of Exhibits", min_value=0, value=0)
-    long = st.number_input("Conference Duration, Days", min_value=0, value=3)
-    
-    # Dropdown menus
-    event_type = st.selectbox("Event Type", ['Colloquium', 'Conference', 'Forum', 'Seminar', 'Symposium', 'Workshop' , 'Other'], index = 1)
-    cntry = st.selectbox("Conference Location Country", countries, index = us_index)
-    chosen_country_index = countries.index(cntry) 
-    if chosen_country_index == us_index:
-        loc_state = st.selectbox("Conference Location: State Code", states, index=ca_index)
-    else:
-        loc_state = "Other"
-
-    # Checkboxes
-    st.markdown("<h4>Keywords</h4>", unsafe_allow_html=True)
-    kw_comp = st.checkbox("Computer(s) / Computing / Computation / Computational")
-    kw_sys = st.checkbox("System(s)")
-    kw_app = st.checkbox("Application(s)")
-    #kw_ntwk = st.checkbox("Network(s) /Networking")
-    kw_wless = st.checkbox("Wireless")
-    #kw_mdl = st.checkbox("Model / Modeling")
-    #kw_arch = st.checkbox("Architecture(s)")
-    kw_img = st.checkbox("Image / Imaging")
-#    kw_adv = st.checkbox("Advanced")
-#    kw_dist = st.checkbox("Distributed")
-    
-    st.write("**Please only use the exact keywords listed and avoid including any variations or additional words!**")
-submit = st.button("Submit")
-
-# If the submit button is clicked, show output in the second column (col2)
-with col2:
-    if submit:
-        if chosen_country_index != us_index and loc_state != "Other":
-            st.error("Correct Event Location: Country and State!")
-        else:
-            
-            try:
-                p = True
-                regressor = joblib.load("budget_prediction_model.joblib")
-            except:
-                p = False
-              
-            if not p:
-                st.write('Check the model path')
-                st.error("Model doesn't Exist!")
-            else:
-               
-                atnd_num = atnd_num / 1.22
-                ppr_num = ppr_num / 1.26
-                
-                
-                data = pd.DataFrame([{
-                                        'act_atnd_tot_atnd_num': atnd_num,
-                                        'long_atnd_ratio':long/atnd_num, 
-                                        'act_paprs_num': ppr_num, 
-                                        'longevity': long,
-                                        'papr_atnd_ratio':ppr_num/atnd_num, 
-                                        'exh_num': exh_num,
-                                        'conf_loc_cntry_nm_India': int(chosen_country_index == in_index),
-                                        'conf_loc_cntry_nm_USA': int(chosen_country_index == us_index),
-                                        'comput': int(kw_comp),
-                                        'conf_loc_state_nm_CA': int(loc_state == "CA"),
-                                        'system': int(kw_sys),
-                                        'conf_evnt_typ_nm_Conference': int(event_type == "Conference"),
-                                        'applic': int(kw_app),
-                                        'conf_evnt_typ_nm_Workshop': int(event_type == "Workshop"),
-                                        'imag': int(kw_img),
-                                        'wireless': int(kw_wless), 
-                                    
-                }])
-            
-                
-                
-                lambdas = pd.read_csv('lambdas_yeojohnson.csv', header=None, index_col=0)
-                lambdas = lambdas.to_dict()[1]
-                
-                for n in ['act_atnd_tot_atnd_num', 'exh_num', 'act_paprs_num']:
-                    data[n] = yeojohnson(data[n], lambdas[n])
-                data.longevity -= 1
-        
-                # Predict income
-                income = regressor.predict(data)[0]
-                
-                if exh_num > 0:
-                    reg_fees_inc = 0.995 * income
-                else:
-                    reg_fees_inc = income
-                 
-                income = inv_transform.inv_yeojohnson(income, lambdas['fin_inc_tot_amt'])
-                reg_fees_inc = inv_transform.inv_yeojohnson(reg_fees_inc, lambdas['fin_inc_tot_amt'])
-                print(reg_fees_inc)
-                income = math.ceil(income / 1000) * 1000
-                reg_fees_inc = math.ceil(reg_fees_inc / 1000) * 1000
-                
-                exh_inc = 0
-                sponsor_inc = 0
-                
-                if exh_num < 10:
-                    exh_inc = min(exh_num * 1000, income - reg_fees_inc)     
-                elif exh_num < 30:
-                    exh_inc = min(10*1000 + (exh_num-10) * 1500, income - reg_fees_inc)
-                elif exh_num < 50:
-                    exh_inc = min(10*1000 + 20 * 1500 + (exh_num-30) * 3500, income - reg_fees_inc)
-                else:
-                    exh_inc = min(10*1000 + 20 * 1500 + 20 * 3500  + (exh_num-50) * 2900, income - reg_fees_inc)
-                    
-                    
-                # repeat piecewise function for grants and donations
-                if exh_num < 50:
-                    sponsor_inc = min(exh_num * 3900, income - reg_fees_inc - exh_inc)
-                else:
-                    sponsor_inc = min(50 * 3900, income - reg_fees_inc - exh_inc)
-                
-                sponsor_inc = math.ceil(sponsor_inc / 1000) * 1000
-                exh_inc = math.ceil(exh_inc / 1000) * 1000
-                other_inc = income - reg_fees_inc - exh_inc - sponsor_inc
-                reg_fees_inc = reg_fees_inc + other_inc
-                
-                
-                expenses =  math.ceil(income * 0.85 / 1000) * 1000
-                socl_funcs_exp = math.ceil(expenses * 0.54 / 1000) * 1000
-                local_arr_exp = math.ceil(expenses * 0.30 / 1000) * 1000
-                admintn_exp = math.ceil(expenses * 0.07 / 1000) * 1000
-                promo_exp = math.ceil(expenses * 0.04 / 1000) * 1000
-                audit_exp = min(expenses*0.006, 6000)
-                audit_exp = math.ceil(audit_exp / 1000) * 1000
-                other_exp = 0.05*expenses - audit_exp
-                
-                # Display results
-                st.markdown("### Predicted Budget*")
-                st.markdown("<h4>Income Structure</h4>", unsafe_allow_html=True)
-                st.write(f"**Total Income: ${income}**")
-                st.write(f"Registration Fees Income: ${reg_fees_inc}")
-                st.write(f"Exhibit Income: ${exh_inc}")
-                st.write(f"Sponsorship Income: ${sponsor_inc}")
-                #st.write(f"Other Income: ${other_inc}")
-                st.markdown("<h4>Expenses Structure</h4>", unsafe_allow_html=True)
-                st.write(f"**Total Expenses: ${round(round(expenses, -3))}**")
-                st.write(f"Social Functions Expenses: ${round(round(socl_funcs_exp, -3))}")
-                st.write(f"Local Arrangement Expenses: ${round(round(local_arr_exp, -3))}")
-                st.write(f"Administration Expenses: ${round(round(admintn_exp, -3))}")
-                st.write(f"Promotion Expenses Amount: ${round(round(promo_exp, -3))}")
-                st.write(f"Audit Fees Expenses: ${audit_exp}")
-                st.write(f"Other Expenses: ${round(round(other_exp, -3))}")
-                st.write("")
-                st.write("***The numbers are approximate and should be adjusted according to event needs**")
-                
-                # Add button save those numbers to Excel
+import streamlit as st
+import joblib
+import pandas as pd
+from scipy.stats import yeojohnson
+import inv_transform
+import math
+
+
+
+# Title of the app
+st.title("Event Budget Estimate")
+
+# Add custom CSS for spacing between columns
+st.markdown(
+    """
+    <style>
+    .stColumn > div {
+        padding: 10px; /* Adjust the value as needed to increase spacing */
+    }
+    h2 {
+        font-size: 20px;
+    }
+    </style>
+    """, unsafe_allow_html=True)
+
+# Create columns with adjusted spacing
+col1, col2 = st.columns([1, 1], gap="large")  # Adjust gap as needed
+
+with col1:
+    # Smaller column title
+    #st.subheader("Event Data")
+    st.markdown("### Event Data")
+    
+    countries = pd.read_csv('ISO-3166-Countries-with-Regional-Codes.csv')
+    countries_a2 = list (countries['alpha-2'])
+    countries_names = list (countries['name'])
+    countries = [f"{a2} - {name}" for a2, name in zip(countries_a2, countries_names)]
+        
+    us_index = countries_a2.index('US')
+    #cn_index = countries_a2.index('CN')
+    in_index = countries_a2.index('IN')
+    
+    states = pd.read_csv('USA States.csv', index_col=0)
+    states = list(states.Abbreviation)
+    ca_index = states.index('CA')
+    
+    # Input fields
+    atnd_num = st.number_input("Estimate Number of Attendees", min_value=0, value=180)
+    ppr_num = st.number_input("Estimate Paper Number", min_value=0, value=100)
+    exh_num = st.number_input("Estimate Number of Exhibits", min_value=0, value=0)
+    long = st.number_input("Conference Duration, Days", min_value=0, value=3)
+    
+    # Dropdown menus
+    event_type = st.selectbox("Event Type", ['Colloquium', 'Conference', 'Forum', 'Seminar', 'Symposium', 'Workshop' , 'Other'], index = 1)
+    cntry = st.selectbox("Conference Location Country", countries, index = us_index)
+    chosen_country_index = countries.index(cntry) 
+    if chosen_country_index == us_index:
+        loc_state = st.selectbox("Conference Location: State Code", states, index=ca_index)
+    else:
+        loc_state = "Other"
+
+    # Checkboxes
+    st.markdown("<h4>Keywords</h4>", unsafe_allow_html=True)
+    kw_comp = st.checkbox("Computer(s) / Computing / Computation / Computational")
+    kw_sys = st.checkbox("System(s)")
+    kw_app = st.checkbox("Application(s)")
+    #kw_ntwk = st.checkbox("Network(s) /Networking")
+    kw_wless = st.checkbox("Wireless")
+    #kw_mdl = st.checkbox("Model / Modeling")
+    #kw_arch = st.checkbox("Architecture(s)")
+    kw_img = st.checkbox("Image / Imaging")
+#    kw_adv = st.checkbox("Advanced")
+#    kw_dist = st.checkbox("Distributed")
+    
+    st.write("**Please only use the exact keywords listed and avoid including any variations or additional words!**")
+submit = st.button("Submit")
+
+# If the submit button is clicked, show output in the second column (col2)
+with col2:
+    if submit:
+        if chosen_country_index != us_index and loc_state != "Other":
+            st.error("Correct Event Location: Country and State!")
+        else:
+            
+            try:
+                p = True
+                regressor = joblib.load("budget_prediction_model.joblib")
+            except:
+                p = False
+              
+            if not p:
+                st.write('Check the model path')
+                st.error("Model doesn't Exist!")
+            else:
+               
+                atnd_num = atnd_num / 1.22
+                ppr_num = ppr_num / 1.26
+                
+                
+                data = pd.DataFrame([{
+                                        'act_atnd_tot_atnd_num': atnd_num,
+                                        'long_atnd_ratio':long/atnd_num, 
+                                        'act_paprs_num': ppr_num, 
+                                        'longevity': long,
+                                        'papr_atnd_ratio':ppr_num/atnd_num, 
+                                        'exh_num': exh_num,
+                                        'conf_loc_cntry_nm_India': int(chosen_country_index == in_index),
+                                        'conf_loc_cntry_nm_USA': int(chosen_country_index == us_index),
+                                        'comput': int(kw_comp),
+                                        'conf_loc_state_nm_CA': int(loc_state == "CA"),
+                                        'system': int(kw_sys),
+                                        'conf_evnt_typ_nm_Conference': int(event_type == "Conference"),
+                                        'applic': int(kw_app),
+                                        'conf_evnt_typ_nm_Workshop': int(event_type == "Workshop"),
+                                        'imag': int(kw_img),
+                                        'wireless': int(kw_wless), 
+                                    
+                }])
+            
+                
+                
+                lambdas = pd.read_csv('lambdas_yeojohnson.csv', header=None, index_col=0)
+                lambdas = lambdas.to_dict()[1]
+                
+                for n in ['act_atnd_tot_atnd_num', 'exh_num', 'act_paprs_num']:
+                    data[n] = yeojohnson(data[n], lambdas[n])
+                data.longevity -= 1
+        
+                # Predict income
+                income = regressor.predict(data)[0]
+                
+                if exh_num > 0:
+                    reg_fees_inc = 0.995 * income
+                else:
+                    reg_fees_inc = income
+                 
+                income = inv_transform.inv_yeojohnson(income, lambdas['fin_inc_tot_amt'])
+                reg_fees_inc = inv_transform.inv_yeojohnson(reg_fees_inc, lambdas['fin_inc_tot_amt'])
+                print(reg_fees_inc)
+                income = math.ceil(income / 1000) * 1000
+                reg_fees_inc = math.ceil(reg_fees_inc / 1000) * 1000
+                
+                exh_inc = 0
+                sponsor_inc = 0
+                
+                if exh_num < 10:
+                    exh_inc = min(exh_num * 1000, income - reg_fees_inc)     
+                elif exh_num < 30:
+                    exh_inc = min(10*1000 + (exh_num-10) * 1500, income - reg_fees_inc)
+                elif exh_num < 50:
+                    exh_inc = min(10*1000 + 20 * 1500 + (exh_num-30) * 3500, income - reg_fees_inc)
+                else:
+                    exh_inc = min(10*1000 + 20 * 1500 + 20 * 3500  + (exh_num-50) * 2900, income - reg_fees_inc)
+                    
+                    
+                # repeat piecewise function for grants and donations
+                if exh_num < 50:
+                    sponsor_inc = min(exh_num * 3900, income - reg_fees_inc - exh_inc)
+                else:
+                    sponsor_inc = min(50 * 3900, income - reg_fees_inc - exh_inc)
+                
+                sponsor_inc = math.ceil(sponsor_inc / 1000) * 1000
+                exh_inc = math.ceil(exh_inc / 1000) * 1000
+                other_inc = income - reg_fees_inc - exh_inc - sponsor_inc
+                reg_fees_inc = reg_fees_inc + other_inc
+                
+                
+                expenses =  math.ceil(income * 0.85 / 1000) * 1000
+                socl_funcs_exp = math.ceil(expenses * 0.54 / 1000) * 1000
+                local_arr_exp = math.ceil(expenses * 0.30 / 1000) * 1000
+                admintn_exp = math.ceil(expenses * 0.07 / 1000) * 1000
+                promo_exp = math.ceil(expenses * 0.04 / 1000) * 1000
+                audit_exp = min(expenses*0.006, 6000)
+                audit_exp = math.ceil(audit_exp / 1000) * 1000
+                other_exp = expenses - socl_funcs_exp - local_arr_exp - admintn_exp - promo_exp - audit_exp
+                
+                # Display results
+                st.markdown("### Predicted Budget*")
+                st.markdown("<h4>Income Structure</h4>", unsafe_allow_html=True)
+                st.write(f"**Total Income: ${income}**")
+                st.write(f"Registration Fees Income: ${reg_fees_inc}")
+                st.write(f"Exhibit Income: ${exh_inc}")
+                st.write(f"Sponsorship Income: ${sponsor_inc}")
+                #st.write(f"Other Income: ${other_inc}")
+                st.markdown("<h4>Expenses Structure</h4>", unsafe_allow_html=True)
+                st.write(f"**Total Expenses: ${round(round(expenses, -3))}**")
+                st.write(f"Social Functions Expenses: ${round(round(socl_funcs_exp, -3))}")
+                st.write(f"Local Arrangement Expenses: ${round(round(local_arr_exp, -3))}")
+                st.write(f"Administration Expenses: ${round(round(admintn_exp, -3))}")
+                st.write(f"Promotion Expenses Amount: ${round(round(promo_exp, -3))}")
+                st.write(f"Audit Fees Expenses: ${audit_exp}")
+                st.write(f"Other Expenses: ${round(round(other_exp, -3))}")
+                st.write("")
+                st.write("***The numbers are approximate and should be adjusted according to event needs**")
+                
+                # Add button save those numbers to Excel