Scenario
Recall our farming scenario, in which we want to look at how January temperatures have changed over time. Now we'll build a model that achieves this by using supervised learning.
import pandas
!wget <https://raw.githubusercontent.com/MicrosoftDocs/mslearn-introduction-to-machine-learning/main/graphing.py>
!wget <https://raw.githubusercontent.com/MicrosoftDocs/mslearn-introduction-to-machine-learning/main/m0b_optimizer.py>
!wget <https://raw.githubusercontent.com/MicrosoftDocs/mslearn-introduction-to-machine-learning/main/Data/seattleWeather_1948-2017.csv>
# Load a file that contains weather data for Seattle
data = pandas.read_csv('seattleWeather_1948-2017.csv', parse_dates=['date'])
# Keep only January temperatures
data = data[[d.month == 1 for d in data.date]].copy()
# Print the first and last few rows
# Remember that with Jupyter notebooks, the last line of
# code is automatically printed
data
| Element | Description |
|---|---|
| The problem of … | diseases related to rice crop |
| Affects … | farmers, workers(millers, transporters, and traders), consumers |
| And result in … | lower farm yields, reduce the availability and quality of rice for consumption, lower employment opportunities and income for workers |
| Benefits of solution … | Reduced crop losses, Lower production costs, Improved yield and quality,Better marketability, Reduced environmental impact, Improved food security |
| Source | Constraint | Rationale |
|---|---|---|
| System | software must be <1Gb and should run under 1Gb RAM | due to limited memory due to cost constraints |
| Equipment budget | integrated system must cost under 50,000 inr | in order for system to be viable for small farmer the cost of system should be reasonable |
| Technology stack | object-oriented methodology should be used with reliable standards | this will ensure frictionless scalability in future |
| Accuracy and sensitivity | accuracy should be >80% and system must accommodate to indian environment with ranged sensitivity of >0.8 | this will ensure reliability and sustainability |
| Speed of detection | must be able to detect atleast 3 crops a second keeping in mind density of crop sown | this will ensure proper working in large farms of multiple Acres |