Upload 4 files

app.py

@@ -0,0 +1,122 @@
+import streamlit as st
+import pandas as pd
+import pickle
+from sklearn.impute import SimpleImputer
+from sklearn.utils.validation import check_is_fitted
+
+# Load the trained model and preprocessing objects using pickle
+with open('random_forest_model.pkl', 'rb') as f:
+    random_forest_model = pickle.load(f)
+
+with open('scaler.pkl', 'rb') as f:
+    scaler = pickle.load(f)
+
+with open('label_encoders.pkl', 'rb') as f:
+    label_encoders = pickle.load(f)
+
+# State corrections and valid states/UTs
+state_corrections = {
+    'uttaranchal': 'uttarakhand',
+    'orissa (odisha)': 'odisha',
+    'kashmir': 'jammu and kashmir',
+    'multi state': 'other',
+    'not classified': 'other'
+}
+
+valid_states_uts = [
+    'andhra pradesh', 'arunachal pradesh', 'assam', 'bihar', 'chhattisgarh', 'goa',
+    'gujarat', 'haryana', 'himachal pradesh', 'jharkhand', 'karnataka', 'kerala',
+    'madhya pradesh', 'maharashtra', 'manipur', 'meghalaya', 'mizoram', 'nagaland',
+    'odisha', 'punjab', 'rajasthan', 'sikkim', 'tamil nadu', 'telangana', 'tripura',
+    'uttar pradesh', 'uttarakhand', 'west bengal', 'andaman and nicobar islands',
+    'chandigarh', 'dadra and nagar haveli and daman and diu', 'lakshadweep', 'delhi',
+    'puducherry', 'jammu and kashmir', 'ladakh'
+]
+
+# Extract city, state, and country
+def extract_city(x):
+    if isinstance(x, str):
+        splitted_string = x.split("-")
+        if len(splitted_string) == 4:
+            return f"{splitted_string[0].strip().lower()} {splitted_string[1].strip().lower()}"
+        else:
+            return splitted_string[0].strip().lower()
+    else:
+        return "other"
+
+def extract_state(x):
+    if isinstance(x, str):
+        state = x.split("-")[-2].strip().lower()
+        return state_corrections.get(state, state if state in valid_states_uts else 'other')
+    else:
+        return "other"
+
+def extract_country(x):
+    if isinstance(x, str):
+        return x.split("-")[-1].strip().lower()
+    else:
+        return "other"
+
+def preprocess_new_data(df):
+    df['Ownership'] = df['Ownership'].str.lower().str.strip()
+    df[' Type of Tender '] = df[' Type of Tender '].str.lower().str.strip()
+
+    def parse_closing_date(date_str):
+        try:
+            return pd.to_datetime(date_str)
+        except Exception:
+            if " to " in date_str:
+                date_str = date_str.split(" to ")[-1]
+                return pd.to_datetime(date_str, errors='coerce')
+            return pd.NaT
+
+    df['Closing Date'] = df['Closing Date'].apply(parse_closing_date)
+    df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
+    df['days_left'] = (df['Closing Date'] - df['Date']).dt.days
+
+    df['city'] = df['Location'].apply(lambda x: extract_city(x))
+    df['state'] = df['Location'].apply(lambda x: extract_state(x))
+    df['country'] = df['Location'].apply(lambda x: extract_country(x))
+
+    df['city'].fillna("other", inplace=True)
+    df['state'].fillna("other", inplace=True)
+    df['country'].fillna("other", inplace=True)
+
+    df = df[['Ref No', 'Earnest Money', 'Estimated Cost', 'DocFees', 'Ownership', ' Type of Tender ', 'days_left', 'city', 'state', 'country']]
+
+    imputer = SimpleImputer(strategy='median')
+    df['days_left'] = imputer.fit_transform(df[['days_left']])
+
+    for column in ['Ownership', ' Type of Tender ', 'city', 'state', 'country']:
+        le = label_encoders[column]
+        df[column] = df[column].apply(lambda x: x if x in le.classes_ else 'other')
+        df[column] = le.transform(df[column])
+
+    numerical_features = ['Earnest Money', 'Estimated Cost', 'DocFees', 'days_left']
+    df[numerical_features] = scaler.transform(df[numerical_features])
+
+    return df
+
+def predict_new_data(new_data):
+    preprocessed_data = preprocess_new_data(new_data)
+    X_new = preprocessed_data.drop(columns=['Ref No'])
+    tender_ref_numbers_new = preprocessed_data['Ref No']
+    predictions = random_forest_model.predict(X_new)
+    results = pd.DataFrame({
+        'Ref No': tender_ref_numbers_new,
+        'Selected': predictions
+    })
+    
+    return results
+
+st.title("Tender Selection Prediction")
+uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+if uploaded_file is not None:
+    new_data = pd.read_csv(uploaded_file)
+    prediction_results = predict_new_data(new_data)
+    selected_tenders = prediction_results[prediction_results['Selected'] == "yes"]['Ref No'].astype(str).to_list()
+    new_data['Ref No'] = new_data['Ref No'].astype(str)
+
+    st.write("Selected Tenders:")
+    st.write(new_data[new_data['Ref No'].isin(selected_tenders)].drop(columns=['Unnamed: 0']).reset_index().drop(columns=['index']))

label_encoders.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61fdd47acff081b0938b383ed2a372cbf1ca7eb42fa58717f9e1d966cbbea3c6
+size 19704

random_forest_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc78b9a55f882d8580dcc8971148ab856ba55dfd76d39660d5291dcff10cc3ac
+size 153909782

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baba225548cb3c0765e59d932acb0b4e035bb5c759e3473a524674af63931235
+size 688