Update driverpospredictionfinal.py

driverpospredictionfinal.py

@@ -15,8 +15,6 @@ app = Flask(__name__)
 from sklearn import tree, linear_model
 from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 from sklearn.model_selection import train_test_split, GridSearchCV
-!pip install bayesian-optimization
-from bayes_opt import BayesianOptimization
 from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, mean_squared_log_error, median_absolute_error
 import pandas as pd
 import joblib
@@ -27,10 +25,20 @@ import xgboost as xgb
 import pickle
 
 def read_data(file_name):
-  df = pd.read_csv(file_name)
-  x= df.drop(['RaceID', "Pos", "formating" ], axis=1)
-  y =df["Pos"]
-  return x,y
+    df = pd.read_csv(file_name)
+
+    # Convert 'LapTime' column to numeric (removing 'days' and 'seconds' part)
+    df['LapTime'] = pd.to_timedelta(df['LapTime']).dt.total_seconds()
+
+    # Encoding categorical columns (like 'Compound' and 'Compound2')
+    label_encoder = LabelEncoder()
+    df['Compound'] = label_encoder.fit_transform(df['Compound'])
+    df['Compound2'] = label_encoder.fit_transform(df['Compound2'])
+
+    # Drop non-predictive columns and set target variable
+    X = df.drop(['Race', 'Driver', 'Position', 'Rainfall', 'RainFall2'], axis=1)
+    y = df['Position']
+    return X, y
 
 #returns the object for model being used
 def decision_tree_regressor_method():
@@ -88,16 +96,20 @@ def hyperamter_tuning_paramter_grid():
 def prediction(req):
   data = json.loads(req)
   input_data = {}
-  input_data['LapNumber'] = float(data['lapNumber'])
-  input_data['LapTimes'] = float(data['LapTimes'])
-  input_data['PitStopTimes'] = float(data['PitStopTimes'])
-  input_data['PrevLap'] = float(data['PrevLap'])
-  input_data['AvgSpeed'] = float(data['AvgSpeed'])
-  input_data['AirTemp_Cel'] = float(data['AirTemp_Cel'])
-  input_data['TrackTemp_Cel'] = float(data['TrackTemp_Cel'])
-  input_data['Humidity'] = float(data['Humidity'])
-  input_data['WindSpeed_km'] = float(data['WindSpeed_km'])
-  print(input_data)
+
+  input_data['LapNumber'] = float(input("Enter the number of total laps in race: "))
+  input_data['LapTime'] = float(input("Avg lap time from prev year (in seconds): "))
+  input_data['TyreLife'] = float(input("Enter tyre life (in laps): "))
+  input_data['Speedl1'] = float(input("Enter Speedl1 (in km/h): "))
+  input_data['Speedl2'] = float(input("Enter Speedl2 (in km/h): "))
+  input_data['SpeedFL'] = float(input("Enter SpeedFL (in km/h): "))
+  input_data['SpeedST'] = float(input("Enter SpeedST (in km/h): "))
+  input_data['AirTemp'] = float(input("Enter air temperature in Celsius: "))
+  input_data['TrackTemp'] = float(input("Enter track temperature in Celsius: "))
+  input_data['Humidity'] = float(input("Enter humidity percentage (0-100): "))
+  input_data['WindSpeed'] = float(input("Enter wind speed in km/h: "))
+  input_data['Compound'] = float(input("Enter compound (numeric): "))
+  input_data['Compound2'] = float(input("Enter compound2 (numeric): "))
   return jsonify({'message':'Hello world'})
 
 
@@ -150,52 +162,26 @@ def ask_user(model, X_test=None):
 
 
 
+X, y = read_data("b.csv")
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
 
+# Train and evaluate models
+# model_1 = linear_reg(X_train, y_train)
+# y_pred_1 = predict(model_1, X_test, y_test)
 
-#-----linear regresssion------------
-x , y= read_data("b.csv")
-xtrain, xtest , ytrain, ytest = train_test_split(x,y,test_size = 0.3)
-
-model_1 = linear_reg(xtrain,ytrain)
-
-ypred = predict(model_1,xtest,ytest)
-#visvualize(ytest,ypred)
-
-#-----descision tree classifier-----
-x , y= read_data("b.csv")
-xtrain, xtest , ytrain, ytest = train_test_split(x,y,test_size = 0.3)
-
-model_2 = decsison_tree_classifier_method(xtrain,ytrain)
-
-parameter_grid= hyperamter_tuning_paramter_grid()
-tuned_model_2 = hyper_paramter_tuning(model_2,xtrain,ytrain,**parameter_grid)
-y_pred = predict(tuned_model_2,xtest,ytest)
-
-#visvualize(ytest,ypred)
-
-#----descision tree regressor-------
-x , y= read_data("b.csv")
-xtrain, xtest , ytrain, ytest = train_test_split(x,y,test_size = 0.3)
+#model_2 = decision_tree_classifier_method(X_train, y_train)
+parameter_grid = hyperparameter_tuning_paramter_grid()
+# tuned_model_2 = hyper_paramter_tuning(model_2, X_train, y_train, **parameter_grid)
+# y_pred_2 = predict(tuned_model_2, X_test, y_test)
 
 model_3 = decision_tree_regressor_method()
-
-parameter_grid= hyperamter_tuning_paramter_grid()
-tuned_model_3 = hyper_paramter_tuning(model_3,xtrain,ytrain,**parameter_grid)
-y_pred= predict(tuned_model_3,xtest,ytest)
-
-
-with open('model.pkl', 'wb') as file:
-    pickle.dump(tuned_model_3, file)
-
-
+tuned_model_3 = hyper_paramter_tuning(model_3, X_train, y_train, **parameter_grid)
+y_pred_3 = predict(tuned_model_3, X_test, y_test)
 
 # Ask user for input and predict position
-#predicted_position = ask_user(tuned_model_3, x_columns)
+predicted_position = ask_user(tuned_model_3, X_test)
 
-
-
-
-#predicted_position = ask_user(tuned_model_3, xtest)
-
-#pickle.dump(tuned_model_3.open('model.pkl','mb'))
+# Save model
+with open('tuned_model.pkl', 'wb') as file:
+    pickle.dump(tuned_model_3, file)