Project: Predicting Temperature in London

As the climate changes, predicting the weather becomes ever more important for businesses. You have been asked to support on a machine learning project with the aim of building a pipeline to predict the climate in London, England. Specifically, the model should predict mean temperature in degrees Celsius (°C).

Since the weather depends on a lot of different factors, you will want to run a lot of experiments to determine what the best approach is to predict the weather. In this project, you will run experiments for different regression models predicting the mean temperature, using a combination of sklearn and mlflow.

You will be working with data stored in london_weather.csv, which contains the following columns:

date - recorded date of measurement - (int)
cloud_cover - cloud cover measurement in oktas - (float)
sunshine - sunshine measurement in hours (hrs) - (float)
global_radiation - irradiance measurement in Watt per square meter (W/m2) - (float)
max_temp - maximum temperature recorded in degrees Celsius (°C) - (float)
mean_temp - target mean temperature in degrees Celsius (°C) - (float)
min_temp - minimum temperature recorded in degrees Celsius (°C) - (float)
precipitation - precipitation measurement in millimeters (mm) - (float)
pressure - pressure measurement in Pascals (Pa) - (float)
snow_depth - snow depth measurement in centimeters (cm) - (float)

Hidden code

# 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

# Read in the data
weather = pd.read_csv("london_weather.csv")

# Perform exploratory data analysis and data cleaning
weather.info()

# Convert date and extract information
weather["date"] = pd.to_datetime(weather["date"], format="%Y%m%d")
weather["year"] = weather["date"].dt.year
weather['month'] = weather['date'].dt.month

# Aggregate and calculate average metrics
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()

# Visualize relationships in the data
sns.lineplot(x="year", y="mean_temp", data=weather_per_month, ci=None)
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'])

# Subset feature and target sets
X = weather[feature_selection]    
y = weather[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)

# Predict, evaluate, and log the parameters and metrics of your models
for idx, depth in enumerate([1, 2, 5, 10, 20]): 
    run_name = f"run_{idx}"
    with mlflow.start_run(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
        y_pred_lin_reg = lin_reg.predict(X_test)
        lin_reg_rmse = mean_squared_error(y_test, y_pred_lin_reg, squared=False)
        y_pred_tree_reg = tree_reg.predict(X_test)
        tree_reg_rmse = mean_squared_error(y_test, y_pred_tree_reg, squared=False)
        y_pred_forest_reg = forest_reg.predict(X_test)
        forest_reg_rmse = mean_squared_error(y_test, y_pred_forest_reg, squared=False)
        # 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_results