Agriculture Data Processing with Python

Link to the code: https://github.com/Chauloroches/Agricultural_Data_Processing_Python

Cleaned, processed, and visualized agricultural datasets using Python and pandas, identifying key trends that informed productivity improvements and sales forecasting

This project has two files:

crop_production.csv

Sales_Data

Cleaning Data

Provide summary details of sales and production data as shown below:

sales.info()

production.info()

This helps me know how the data is and how many rows and columns it has.

I also check for quick statistics in our data frames in the numerical columns:

sales.describe()

production.describe()

I then check for total missing values in sales and production as shown below:

sales.isnull().sum()

production.isnull().sum()

I then check for duplicates in both data frames:

sales.duplicated()

production.duplicated()

I now remove duplicates to ensure the data frames are clean:

remove_sales_duplicates = sales.drop_duplicates()

remove_production_duplicates = production.drop_duplicates()

remove_production_duplicates

remove_sales_duplicates

Exploratory Data Analysis (EDA)

1. To find top crops by yield.

top_crops = production.groupby("Crop")["Yield_per_Hectare"].mean().sort_values(ascending=False)

top_crops

2. Monthly trends in sales volume:

monthly_sales = sales.groupby("Month")["Sales_Volume"].sum()

monthly_sales

3. Seasonal trends:

seasons_yield = production.groupby(['Season','Crop'])["Yield_per_Hectare"].mean().unstack()

seasons_yield

Visualization

1. Plotting Bar chart of average yield per crop and we used a bar graph for this:

top_crops.plot(kind="bar", figsize=(8, 5),colormap="Set2")

plt.ylabel("Yield (tons per hectare)",labelpad=10)

plt.xlabel("Crop",labelpad=10)

plt.title("Average Yield per Crop",y=1.02)

plt.show()

2. Plotting Line chart of Monthly sales

This line plot shows the total sales volume for each month, making it easy to spot any seasonal patterns in sales

monthly_sales.plot(kind="line", figsize=(6, 4),marker="o")

plt.ylabel("Sales Volume (tons)",labelpad=10)

plt.xlabel("Month",labelpad=10)

plt.title("Monthly Sales Volume",y=1.02)

plt.grid(True)

plt.xticks(range(1,13))

plt.show()

3. Plotting Seasonal Yield Trends for all the crops

   seasons_yield.plot(kind='bar',figsize=(8,5),colormap="Set2")

   plt.xlabel('Crop',labelpad=10)

   plt.ylabel('Yield(Tonnes per Hectares)',labelpad=10)

   plt.title('Seasonal Yield per Hectares',y=1.02)

   plt.xticks(rotation=45)

   plt.tight_layout()

   plt.show()

4. 
   

   

   Insights and Report

   Having done the analysis and visualization we concluded two major things:

   1. The crop with the highest yield was Maize and Soybean was the lowest

   2. The months with the highest sales volumes were months 6 and 4.