Mali-shaikh/WeatherProject

Weather Predication ## 📘 Overview This project analyzes historical weather data to predict future weather conditions using supervised machine learning. It walks through a complete data science workflow --- from preprocessing to model evaluation. ------------------------------------------------------------------------ ## 🧩 Objectives - Load and explore the weather dataset\ - Clean, encode, and scale the data\ - Select the most relevant features\ - Train and evaluate classification models\ - Optimize model parameters and compare results ------------------------------------------------------------------------ ## 🛠️ Technologies Used - **Python 3.x**\ - **pandas** -- data manipulation\ - **scikit-learn** -- preprocessing, model building, and evaluation\ - **NumPy** -- numerical computation\ - *(Optional)* **Matplotlib / Seaborn** -- visualization ------------------------------------------------------------------------ ## ⚙️ Workflow Summary 1. **Data Loading** - Load the dataset `Weather Data.csv` using pandas. 2. **Data Preprocessing** - Handle missing values with `SimpleImputer` - Encode categorical variables with `LabelEncoder` or `OneHotEncoder` - Scale numerical features using `StandardScaler` or `MinMaxScaler` 3. **Feature Selection** - Apply `SelectKBest` using the chi-square (`chi2`) method to retain top predictors. 4. **Model Building** - Train and compare: - **Logistic Regression** - **Decision Tree Classifier** - Split data into training and test sets using `train_test_split`. 5. **Model Evaluation** - Evaluate performance using: - **Accuracy Score** - **Classification Report (Precision, Recall, F1)** - **Confusion Matrix** - **F2 Score** - Tune Decision Tree using varying depths to balance training and testing accuracy. ------------------------------------------------------------------------ ## 📊 Results ------------------------------------------------------------------------------------ Model Accuracy …