讲解data编程、讲解Java，Python编程语言、Python程序辅导
- 首页 >> Python编程 Problem Description: Sustainability of the human race in different parts of the world is
challenged by the shortage of food. The world population has grown six hundred
percentage - from one billion to about six billion - in the last two hundred years. According
to the Population Institute, roughly, 230 thousand more babies are born every day. The
World Food Programme estimates that about 795 million people do not have adequate
food to lead a healthy life. About 3.1 million children die every year because of poor
nutrition. On the other hand, land used for farming has been decreasing which makes the
burden of food shortage acute. Regardless, simply attempting to increase the land
available for farming is unlikely to sustain the needed food supply. To address this great
problem, this project expects you to develop an analytics framework to aid soybean
farmers select up to a given number of varieties of soybeans from a large set of available
varieties to maximize the yield at a target farm.
Every year soybean farmers make decisions about the varieties to be grown at their farm.
While making this decision, they consider uncertainty due to weather, soil conditions, and
yield studies of different varieties. They could choose just one variety or a mix of few
varieties to hedge against uncertainties. You are expected to utilize the dataset provided
to propose a framework which integrates descriptive, predictive, and prescriptive analytics
to optimally select up to five varieties of soybeans.
Deliverables:
1. Perform exploratory data analytics to unearth patterns in the given data and utilize
those patterns in making predictions and prescriptions.
2. Construct one or more prediction models to predict yield of different experimental
varieties.
3. Optimize the portfolio of (experimental) varieties to be grown at the target farm.
The optimal portfolio can have at most 5 varieties of soybean. It is not necessary
but you are welcome to use the methods you learn in prescriptive analytics class
to construct the optimal portfolio.
Data Sets:
1. Training Data for Ag Project
2. Evaluation Dataset for Ag Project
Key:
GrowingSeason Year Date
Location trial location code Id number
Genetics breeding group Group ID
Experiment Experiment number Experiment ID
Latitude Latitude Decimal degrees
Longitude Longitude Decimal degrees
Variety Variety code Variety ID
Variety_Yield Variety yield Bushels per acre adjusted by
moisture
Commercial_Yield Commercial yield for the trial Bushels per acre adjusted by
moisture
Yield_Difference yield difference between
experiment and commercial
varieties in a trial
Bushels per acre adjusted by
moisture
Location_Yield Average site yield (approximately,
checks across experiments)
Bushels per acre adjusted by
moisture
RelativeMaturity Relative Maturity Interval Relative maturity interval
(region) based on the location
Weather1 Climate type based on
temperature, precipitation and
solar radiation
Climate class
Weather2 Season type Season class
Probability Probability of growing soybean Probability of growing
soybeans in the nearby area of
the site
RelativeMaturity25 Probability of growing soybean of
RM 2.5 to 3
Probability of growing
soybeans in the nearby area of
the site
Prob_IRR Probability of irrigation Probability of field
irrgation nearby the area of the
site
Soil_Type Soil type based on texture,
available water holding capacity,
and soil drainage
Soil Class
TEMP_03 Sum of the temperatures for the
season 2003
Daily degree Celsius sum
between April 1st and October
31st
TEMP_04 Sum of the temperatures for the
season 2004
Daily degree Celsius sum
between April 1st and October
31st
TEMP_05 Sum of the temperatures for the
season 2005
Daily degree Celsius sum
between April 1st and October
31st
TEMP_06 Sum of the temperatures for the
season 2006
Daily degree Celsius sum
between April 1st and October
31st
TEMP_07 Sum of the temperatures for the
season 2007
Daily degree Celsius sum
between April 1st and October
31st
TEMP_08 Sum of the temperatures for the
season 2008
Daily degree Celsius sum
between April 1st and October
31st
TEMP_09 Sum of the temperatures for the
season 2009
Daily degree Celsius sum
between April 1st and October
31st
Median_Temp Median Sum of temperatures for
season between 1994 and 2007
Daily degree Celsius sum
between April 1st and October
31st
PREC_03 Sum of the precipitation for the
season 2003
Daily degree Celsius sum
between April 1st and October
31st
PREC_04 Sum of the precipitation for the
season 2004
Precipitation sum between
April 1st and October 31st
PREC_05 Sum of the precipitation for the
season 2005
Precipitation sum between
April 1st and October 31st
PREC_06 Sum of the precipitation for the
season 2006
Precipitation sum between
April 1st and October 31st
PREC_07 Sum of the precipitation for the
season 2007
Precipitation sum between
April 1st and October 31st
PREC_08 Sum of the precipitation for the
season 2008
Precipitation sum between
April 1st and October 31st
PREC_09 Sum of the precipitation for the
season 2009
Precipitation sum between
April 1st and October 31st
Median_Prec Median Sum of precipitation for
season between 1994 and 2007
Precipitation sum between
April 1st and October 31st
RAD_03 Sum of the solar radiation for the
season 2003
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_04 Sum of the solar radiation for the
season 2004
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_05 Sum of the solar radiation for the
season 2005
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_06 Sum of the solar radiation for the
season 2006
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_07 Sum of the solar radiation for the
season 2007
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_08 Sum of the solar radiation for the
season 2008
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_09 Sum of the solar radiation for the
season 2009
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_MED Median Sum of solar radiation for
season between 1994 and 2007
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
PH1 Topsoil ( 10 to 20 cm depth ) pH pH units
AWC1 Topsoil ( 10 to 20 cm depth )
Available water capacity in 150 cm
soil profile
cm
Clay1 Topsoil clay content ( 10 to 20 cm
depth )
Percentage
Silt1 Topsoil silt content ( 10 to 20 cm
depth )
Percentage
Sand1 Topsoil sand content ( 10 to 20 cm
depth )
Percentage
Sand2 Soil sand content from another soil
source
Percentage (5-30 cm)
Silt2 Soil silt content from another soil
source
Percentage (5-30 cm)
Clay2 Soil clay content from another soil
source
Percentage (5-30 cm)
PH2 Soil ph from another soil source pH (5-30 cm)
CEC Soil cation exchange from another
soil source
cmol per kilo (5-30 cm)
CE Soil cation exchange from another
soil source
cmol per kilo (5-30 cm)
challenged by the shortage of food. The world population has grown six hundred
percentage - from one billion to about six billion - in the last two hundred years. According
to the Population Institute, roughly, 230 thousand more babies are born every day. The
World Food Programme estimates that about 795 million people do not have adequate
food to lead a healthy life. About 3.1 million children die every year because of poor
nutrition. On the other hand, land used for farming has been decreasing which makes the
burden of food shortage acute. Regardless, simply attempting to increase the land
available for farming is unlikely to sustain the needed food supply. To address this great
problem, this project expects you to develop an analytics framework to aid soybean
farmers select up to a given number of varieties of soybeans from a large set of available
varieties to maximize the yield at a target farm.
Every year soybean farmers make decisions about the varieties to be grown at their farm.
While making this decision, they consider uncertainty due to weather, soil conditions, and
yield studies of different varieties. They could choose just one variety or a mix of few
varieties to hedge against uncertainties. You are expected to utilize the dataset provided
to propose a framework which integrates descriptive, predictive, and prescriptive analytics
to optimally select up to five varieties of soybeans.
Deliverables:
1. Perform exploratory data analytics to unearth patterns in the given data and utilize
those patterns in making predictions and prescriptions.
2. Construct one or more prediction models to predict yield of different experimental
varieties.
3. Optimize the portfolio of (experimental) varieties to be grown at the target farm.
The optimal portfolio can have at most 5 varieties of soybean. It is not necessary
but you are welcome to use the methods you learn in prescriptive analytics class
to construct the optimal portfolio.
Data Sets:
1. Training Data for Ag Project
2. Evaluation Dataset for Ag Project
Key:
GrowingSeason Year Date
Location trial location code Id number
Genetics breeding group Group ID
Experiment Experiment number Experiment ID
Latitude Latitude Decimal degrees
Longitude Longitude Decimal degrees
Variety Variety code Variety ID
Variety_Yield Variety yield Bushels per acre adjusted by
moisture
Commercial_Yield Commercial yield for the trial Bushels per acre adjusted by
moisture
Yield_Difference yield difference between
experiment and commercial
varieties in a trial
Bushels per acre adjusted by
moisture
Location_Yield Average site yield (approximately,
checks across experiments)
Bushels per acre adjusted by
moisture
RelativeMaturity Relative Maturity Interval Relative maturity interval
(region) based on the location
Weather1 Climate type based on
temperature, precipitation and
solar radiation
Climate class
Weather2 Season type Season class
Probability Probability of growing soybean Probability of growing
soybeans in the nearby area of
the site
RelativeMaturity25 Probability of growing soybean of
RM 2.5 to 3
Probability of growing
soybeans in the nearby area of
the site
Prob_IRR Probability of irrigation Probability of field
irrgation nearby the area of the
site
Soil_Type Soil type based on texture,
available water holding capacity,
and soil drainage
Soil Class
TEMP_03 Sum of the temperatures for the
season 2003
Daily degree Celsius sum
between April 1st and October
31st
TEMP_04 Sum of the temperatures for the
season 2004
Daily degree Celsius sum
between April 1st and October
31st
TEMP_05 Sum of the temperatures for the
season 2005
Daily degree Celsius sum
between April 1st and October
31st
TEMP_06 Sum of the temperatures for the
season 2006
Daily degree Celsius sum
between April 1st and October
31st
TEMP_07 Sum of the temperatures for the
season 2007
Daily degree Celsius sum
between April 1st and October
31st
TEMP_08 Sum of the temperatures for the
season 2008
Daily degree Celsius sum
between April 1st and October
31st
TEMP_09 Sum of the temperatures for the
season 2009
Daily degree Celsius sum
between April 1st and October
31st
Median_Temp Median Sum of temperatures for
season between 1994 and 2007
Daily degree Celsius sum
between April 1st and October
31st
PREC_03 Sum of the precipitation for the
season 2003
Daily degree Celsius sum
between April 1st and October
31st
PREC_04 Sum of the precipitation for the
season 2004
Precipitation sum between
April 1st and October 31st
PREC_05 Sum of the precipitation for the
season 2005
Precipitation sum between
April 1st and October 31st
PREC_06 Sum of the precipitation for the
season 2006
Precipitation sum between
April 1st and October 31st
PREC_07 Sum of the precipitation for the
season 2007
Precipitation sum between
April 1st and October 31st
PREC_08 Sum of the precipitation for the
season 2008
Precipitation sum between
April 1st and October 31st
PREC_09 Sum of the precipitation for the
season 2009
Precipitation sum between
April 1st and October 31st
Median_Prec Median Sum of precipitation for
season between 1994 and 2007
Precipitation sum between
April 1st and October 31st
RAD_03 Sum of the solar radiation for the
season 2003
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_04 Sum of the solar radiation for the
season 2004
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_05 Sum of the solar radiation for the
season 2005
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_06 Sum of the solar radiation for the
season 2006
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_07 Sum of the solar radiation for the
season 2007
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_08 Sum of the solar radiation for the
season 2008
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_09 Sum of the solar radiation for the
season 2009
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
RAD_MED Median Sum of solar radiation for
season between 1994 and 2007
Daily Watts per sq. meter solar
radiation sum between April 1st
and October 31st
PH1 Topsoil ( 10 to 20 cm depth ) pH pH units
AWC1 Topsoil ( 10 to 20 cm depth )
Available water capacity in 150 cm
soil profile
cm
Clay1 Topsoil clay content ( 10 to 20 cm
depth )
Percentage
Silt1 Topsoil silt content ( 10 to 20 cm
depth )
Percentage
Sand1 Topsoil sand content ( 10 to 20 cm
depth )
Percentage
Sand2 Soil sand content from another soil
source
Percentage (5-30 cm)
Silt2 Soil silt content from another soil
source
Percentage (5-30 cm)
Clay2 Soil clay content from another soil
source
Percentage (5-30 cm)
PH2 Soil ph from another soil source pH (5-30 cm)
CEC Soil cation exchange from another
soil source
cmol per kilo (5-30 cm)
CE Soil cation exchange from another
soil source
cmol per kilo (5-30 cm)