# Load libraries
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

# Data Source: https://www.kaggle.com/datasets/samuelotiattakorah/agriculture-crop-yield?resource=download

# Read CSV
df = pd.read_csv("crop_yield.csv")

# Check unique crop values
print(df["Crop"].unique())

# Filter for Maize only
df = df[df["Crop"] == "Maize"]

# Scatter plot: Rainfall vs Yield
plt.figure(figsize=(8, 6))
sns.scatterplot(
    data=df,
    x="Rainfall_mm",
    y="Yield_tons_per_hectare",
    color="#D44803",
    alpha=0.6
)

# Add labels and title
plt.title("Scatter Plots with PikBioStat: Rainfall vs Maize Yield", fontsize=14)
plt.xlabel("Rainfall (mm)")
plt.ylabel("Yield tons per Hectare")

# Remove gridlines (like theme_minimal + no panel.grid in ggplot)
sns.despine()
plt.grid(False)

plt.show()