app.py

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error, r2_score, accuracy_score
from sklearn.linear_model import LinearRegression,Lasso, Ridge
from sklearn.neighbors import KNeighborsRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_absolute_error, r2_score, accuracy_score
from sklearn.svm import SVR
import gradio as gr

df = pd.read_csv("yield_df.csv")
df.head()

# Preprocessing
df.drop_duplicates(inplace = True)
df.duplicated().sum()
col = ['Year', 'average_rain_fall_mm_per_year','pesticides_tonnes', 'avg_temp', 'Area', 'Item', 'hg/ha_yield']
df = df[col]

x = df.drop('hg/ha_yield', axis = 1)
y = df['hg/ha_yield']

x_train, x_test, y_train, y_test =  train_test_split (x,y,test_size = 0.2, random_state= 0, shuffle= True)

ohe = OneHotEncoder(drop='first')
scale = StandardScaler()

preprocessor = ColumnTransformer(
    transformers=[
        ('StandardScale', scale, [0, 1, 2, 3]),
        ('OneHotEncode', ohe, [4, 5])
    ], remainder='passthrough'
)

x_train_dummy = preprocessor.fit_transform(x_train)
x_test_dummy = preprocessor.transform(x_test)

models = {
    #'Linear Regression': LinearRegression(),
    #'Lasso' : Lasso(max_iter=10000),
    #'Ridge' : Ridge(max_iter=10000),
    #'Decision Tree': DecisionTreeRegressor(),
    #'SVR': SVR(),
    #'Random forest': RandomForestRegressor(),
    #'Random forest2': RandomForestRegressor(n_estimators=200),
    'KNN': KNeighborsRegressor(),
}
for name, md in models.items():
    md.fit(x_train_dummy,y_train)
    y_pred = md.predict(x_test_dummy)
    print(f"{name}: mae : {mean_absolute_error(y_test, y_pred)}")
    print(f"{name}: score : {r2_score(y_test, y_pred)}")


# Model Training
model_K = KNeighborsRegressor()
model_K.fit(x_train_dummy, y_train)

# Prediction Function
def prediction(Year, average_rain_fall_mm_per_year, pesticides_tonnes, avg_temp, Area, Item):
    features = np.array([[Year, average_rain_fall_mm_per_year, pesticides_tonnes, avg_temp, Area, Item]], dtype=object)
    transform_features = preprocessor.transform(features)
    predicted_yield = model_K.predict(transform_features).reshape(-1, 1)
    return predicted_yield[0][0]

# Gradio Interface
Areas =['Albania', 'Algeria', 'Angola', 'Argentina', 'Armenia',
       'Australia', 'Austria', 'Azerbaijan', 'Bahamas', 'Bahrain',
       'Bangladesh', 'Belarus', 'Belgium', 'Botswana', 'Brazil',
       'Bulgaria', 'Burkina Faso', 'Burundi', 'Cameroon', 'Canada',
       'Central African Republic', 'Chile', 'Colombia', 'Croatia',
       'Denmark', 'Dominican Republic', 'Ecuador', 'Egypt', 'El Salvador',
       'Eritrea', 'Estonia', 'Finland', 'France', 'Germany', 'Ghana',
       'Greece', 'Guatemala', 'Guinea', 'Guyana', 'Haiti', 'Honduras',
       'Hungary', 'India', 'Indonesia', 'Iraq', 'Ireland', 'Italy',
       'Jamaica', 'Japan', 'Kazakhstan', 'Kenya', 'Latvia', 'Lebanon',
       'Lesotho', 'Libya', 'Lithuania', 'Madagascar', 'Malawi',
       'Malaysia', 'Mali', 'Mauritania', 'Mauritius', 'Mexico',
       'Montenegro', 'Morocco', 'Mozambique', 'Namibia', 'Nepal',
       'Netherlands', 'New Zealand', 'Nicaragua', 'Niger', 'Norway',
       'Pakistan', 'Papua New Guinea', 'Peru', 'Poland', 'Portugal',
       'Qatar', 'Romania', 'Rwanda', 'Saudi Arabia', 'Senegal',
       'Slovenia', 'South Africa', 'Spain', 'Sri Lanka', 'Sudan',
       'Suriname', 'Sweden', 'Switzerland', 'Tajikistan', 'Thailand',
       'Tunisia', 'Turkey', 'Uganda', 'Ukraine', 'United Kingdom',
       'Uruguay', 'Zambia', 'Zimbabwe']

Items = ['Maize', 'Potatoes', 'Rice, paddy', 'Sorghum', 'Soybeans', 'Wheat',
       'Cassava', 'Sweet potatoes', 'Plantains and others', 'Yams']

year_input = gr.Number(label="Year", value=2023)
rainfall_input = gr.Number(label="Average Rainfall (mm per year)", value=1500)
pesticides_input = gr.Number(label="Pesticides (tonnes)", value=120)
temperature_input = gr.Number(label="Average Temperature (°C)", value=16.0)
area_input = gr.Dropdown(choices=Areas, label="Area", multiselect=False)
item_input = gr.Dropdown(choices=Items, label="Item", multiselect=False)

interface = gr.Interface(
    fn=prediction,  # The function to call
    inputs=[year_input, rainfall_input, pesticides_input, temperature_input, area_input, item_input],  
    outputs=gr.Textbox(label="Predicted Crop Yield (hg/ha)"),  
    title="Crop Yield Prediction",
    description="Enter crop and environmental details to predict the crop yield. Use dropdowns for Area and Item."
)

interface = gr.Interface(
    fn=prediction,  # The function to call
    inputs=[year_input, rainfall_input, pesticides_input, temperature_input, area_input, item_input],  
    outputs=gr.Textbox(label="Predicted Crop Yield (hg/ha)"),  
    title="Crop Yield Prediction",
    description="Enter crop and environmental details to predict the crop yield. Use dropdowns for Area and Item."
)

if __name__ == "__main__":
    interface.launch()