Project

# Run this cell to import the modules you require
import pandas as pd
import numpy as np
import mlflow
import mlflow.sklearn
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor

# Import the data and perform exploratory data analysis
weather = pd.read_csv('london_weather.csv')
weather.info()

weather['date'] = pd.to_datetime(weather['date'], format='%Y%m%d')
weather['year'] = weather['date'].dt.year
weather['month'] = weather['date'].dt.month
weather_metrics = ['cloud_cover', 'sunshine', 'global_radiation', 'max_temp', 'mean_temp', 'min_temp', 'precipitation', 'pressure', 'snow_depth']
weather_per_month = weather.groupby(['year', 'month'], as_index = False)[weather_metrics].mean()

sns.lineplot(x="year", y="mean_temp", data=weather_per_month, ci=None)
plt.show()
sns.barplot(x='month', y='precipitation', data=weather)
plt.show()
sns.heatmap(weather.corr(), annot=True)
plt.show()

# Choose features, define the target, and drop null values
feature_selection = ['month', 'cloud_cover', 'sunshine', 'precipitation', 'pressure', 'global_radiation']
target_var = 'mean_temp'
weather = weather.dropna(subset=['mean_temp'])

# Load data and perform exploratory analysis
def preprocess_df(df, feature_selection, target_var):
    """
    Split dataframe into X and y, and train and test consecutively. Then impute and scale both train and test features. Returns the train and test ets
    """
    # Subset the data
    X = df[feature_selection]    
    y = df[target_var]
    
    # Split the data
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=1)
    
    # Impute missing values
    imputer = SimpleImputer(strategy="mean")
    # Fit on the training data
    X_train = imputer.fit_transform(X_train)
    # Transform on the test data
    X_test  = imputer.transform(X_test)
    
    # Scale the data
    scaler = StandardScaler()
    # Fit on the training data
    X_train = scaler.fit_transform(X_train)
    # Transform on the test data
    X_test = scaler.transform(X_test)
    
    return X_train, X_test, y_train, y_test

X_train, X_test, y_train, y_test = preprocess_df(weather, feature_selection, target_var)

# Predict on the test set and evaluate performance
def predict_and_evaluate(model, x_test, y_test):
    """
    Predict values from test set, calculate and return the root mean squared error.
    """
    y_pred = model.predict(x_test)
    rmse = np.sqrt(mean_squared_error(y_test, y_pred))    
    return rmse
  
# Create an experiment
EXPERIMENT_NAME = "weather_prediction"
EXPERIMENT_ID = mlflow.create_experiment(EXPERIMENT_NAME)

# Predict, evaluate, and log the parameters and metrics of your models
for idx, depth in enumerate([1, 2, 5, 10, 20]):
    parameters = {
        'max_depth': depth
    }    
    run_name = f"run_{idx}"
    with mlflow.start_run(experiment_id=EXPERIMENT_ID, run_name=run_name):
        # Create models
        lin_reg = LinearRegression().fit(X_train, y_train)
        tree_reg = DecisionTreeRegressor(random_state=42, max_depth=depth).fit(X_train, y_train)
        forest_reg = RandomForestRegressor(random_state=42, max_depth=depth).fit(X_train, y_train)
        # Log models
        mlflow.sklearn.log_model(lin_reg, "lin_reg")
        mlflow.sklearn.log_model(tree_reg, "tree_reg")
        mlflow.sklearn.log_model(forest_reg, "forest_reg")
        # Evaluate performance
        lin_reg_rmse = predict_and_evaluate(lin_reg, X_test, y_test)
        tree_reg_rmse = predict_and_evaluate(tree_reg, X_test, y_test)
        forest_reg_rmse = predict_and_evaluate(forest_reg, X_test, y_test)
        # Log performance
        mlflow.log_param("max_depth", depth)
        mlflow.log_metric("rmse_lr", lin_reg_rmse)
        mlflow.log_metric("rmse_tr", tree_reg_rmse)
        mlflow.log_metric("rmse_fr", forest_reg_rmse)
        
# Search the runs for the experiment's results
experiment_results = mlflow.search_runs(experiment_names=[EXPERIMENT_NAME])
experiment_results