Comprehensive district-level agricultural database covering 571 districts with 1,030 variables and 11M+ data points on crops, irrigation, infrastructure, and GDP from 1966-2020.
# Download from http://data.icrisat.org/dld/
import pandas as pd
df = pd.read_excel('ICRISAT_DLD.xlsx', sheet_name='Crop')
mh = df[df['State_Name'] == 'Maharashtra']
print(f"Maharashtra records: {len(mh)}")
print(f"Years: {mh['Year'].min()}-{mh['Year'].max()}")
print(f"Districts: {mh['District_Name'].nunique()}")| Field | Type | Description |
|---|---|---|
| district_code | string | Unique district identifier |
| district_name | string | District name |
| state_name | string | State name (filter for Maharashtra) |
| year | int | Data year (1966-2020) |
| variable_name | string | Variable name (crop area, yield, rainfall, irrigation, GDP, etc.) |
| value | float | Observed value for the variable |