def pyunit_apply():
fr = h2o.import_file(pyunit_utils.locate("smalldata/logreg/prostate.csv"))
fr.apply(lambda x: x["PSA"], axis=1).show()
print
print
print fr.apply(lambda x: x['PSA'] > x['VOL'], axis=1).show()
print
zz = fr.apply(lambda x: x.mean(na_rm=True))
print zz.show()
zz = fr.apply(lambda row: row + 2, axis=1)
print zz.show()
zz = fr.apply(lambda row: h2o.ifelse(row[0] == 1, row[2], row[3]), axis=1)
print zz.show()
fr.apply(lambda col: col.abs()).show()
fr.apply(lambda col: col.cos()).show()
fr.apply(lambda col: col.sin()).show()
fr.apply(lambda col: col.ceil()).show()
fr.apply(lambda col: col.floor()).show()
fr.apply(lambda col: col.cosh()).show()
fr.apply(lambda col: col.exp()).show()
fr.apply(lambda col: col.log()).show()
fr.apply(lambda col: col.sqrt()).show()
fr.apply(lambda col: col.tan()).show()
fr.apply(lambda col: col.tanh()).show()
fr.apply(lambda col: (col * col - col * 5 * col).abs() - 55 / col).show()
fr.apply(lambda row: h2o.ifelse(row[0] < 5, (row[2] - 3).expm1(),
(row[2] - 999).expm1()),
axis=1)
fr.apply(lambda row: h2o.ifelse(row[0] < 5, (row[2] - 3).expm1(), 55),
axis=1)
fr.apply(lambda row: h2o.ifelse(row[0] < 5, 3, (row[2] - 1).expm1()),
axis=1)
def pyunit_apply():
fr = h2o.import_file(tests.locate("smalldata/logreg/prostate.csv"))
fr.apply(lambda x: x["PSA"], axis=1).show()
print
print
print fr.apply(lambda x: x['PSA'] > x['VOL'],axis=1).show()
print
zz = fr.apply(lambda x: x.mean(na_rm=True))
print zz.show()
zz = fr.apply(lambda row: row + 2, axis=1)
print zz.show()
zz = fr.apply(lambda row: h2o.ifelse(row[0] == 1, row[2], row[3]), axis=1)
print zz.show()
fr.apply(lambda col: col.abs()).show()
fr.apply(lambda col: col.cos()).show()
fr.apply(lambda col: col.sin()).show()
fr.apply(lambda col: col.ceil()).show()
fr.apply(lambda col: col.floor()).show()
fr.apply(lambda col: col.cosh()).show()
fr.apply(lambda col: col.exp()).show()
fr.apply(lambda col: col.log()).show()
fr.apply(lambda col: col.sqrt()).show()
fr.apply(lambda col: col.tan()).show()
fr.apply(lambda col: col.tanh()).show()
fr.apply(lambda col: (col*col - col*5*col).abs() - 55/col ).show()
fr.apply(lambda row: h2o.ifelse(row[0] < 5, (row[2]-3).expm1(), (row[2] - 999).expm1()), axis=1)
fr.apply(lambda row: h2o.ifelse(row[0] < 5, (row[2]-3).expm1(), 55), axis=1)
fr.apply(lambda row: h2o.ifelse(row[0] < 5, 3, (row[2] - 1).expm1()), axis=1)
def refine_date_col(data, col, pattern):
data[col] = data[col].as_date(pattern)
data["Day"] = data[col].day()
data["Month"] = data[col].month() + 1 # Since H2O indexes from 0
data["Year"] = data[col].year() + 1900 # Start of epoch is 1900
data["WeekNum"] = data[col].week()
data["WeekDay"] = data[col].dayOfWeek()
data["HourOfDay"] = data[col].hour()
# Create weekend and season cols
# Spring = Mar, Apr, May. Summer = Jun, Jul, Aug. Autumn = Sep, Oct. Winter = Nov, Dec, Jan, Feb.
# data["Weekend"] = [1 if x in ("Sun", "Sat") else 0 for x in data["WeekDay"]]
data["Weekend"] = h2o.ifelse(data["WeekDay"] == "Sun" | data["WeekDay"] == "Sat", 1, 0)[0]
data["Season"] = data["Month"].cut([0, 2, 5, 7, 10, 12], ["Winter", "Spring", "Summer", "Autumn", "Winter"])
def refine_date_col(data, col, pattern):
data[col] = data[col].as_date(pattern)
data["Day"] = data[col].day()
data["Month"] = data[col].month() + 1 # Since H2O indexes from 0
data["Year"] = data[col].year() + 1900 # Start of epoch is 1900
data["WeekNum"] = data[col].week()
data["WeekDay"] = data[col].dayOfWeek()
data["HourOfDay"] = data[col].hour()
# Create weekend and season cols
# Spring = Mar, Apr, May. Summer = Jun, Jul, Aug. Autumn = Sep, Oct. Winter = Nov, Dec, Jan, Feb.
# data["Weekend"] = [1 if x in ("Sun", "Sat") else 0 for x in data["WeekDay"]]
data["Weekend"] = h2o.ifelse(data["WeekDay"] == "Sun" | data["WeekDay"] == "Sat", 1, 0)[0]
data["Season"] = data["Month"].cut([0, 2, 5, 7, 10, 12], ["Winter", "Spring", "Summer", "Autumn", "Winter"])
def insert_missing(ip,port):
air_path = [h2o.locate("smalldata/airlines/allyears2k_headers.zip")]
data = h2o.import_file(path=air_path)
hour1 = data["CRSArrTime"] / 100
mins1 = data["CRSArrTime"] % 100
arrTime = hour1*60 + mins1
hour2 = data["CRSDepTime"] / 100
mins2 = data["CRSDepTime"] % 100
depTime = hour2*60 + mins2
data["TravelTime"] = h2o.ifelse((arrTime-depTime)>0,(arrTime-depTime),float("nan"))[0]
data.show()
def refine_date_col(data, col, pattern):
data[col] = data[col].as_date(pattern)
data["Day"] = data[col].day()
data["Month"] = data[col].month() + 1 # Since H2O indexes from 0
data["Year"] = data[col].year() + 1900 # Start of epoch is 1900
data["WeekNum"] = data[col].week()
data["WeekDay"] = data[col].dayOfWeek()
data["HourOfDay"] = data[col].hour()
data.describe() # HACK to force evaluation before the ifelse and cut... basically current execution scheme with Expr is way too restrictive and is going away soon. so we need hacks like this to circumvent type issues and the like
# Create weekend and season cols
# Spring = Mar, Apr, May. Summer = Jun, Jul, Aug. Autumn = Sep, Oct. Winter = Nov, Dec, Jan, Feb.
# data["Weekend"] = [1 if x in ("Sun", "Sat") else 0 for x in data["WeekDay"]]
data["Weekend"] = h2o.ifelse(data["WeekDay"] == "Sun" or data["WeekDay"] == "Sat", 1, 0)[0]
data["Season"] = data["Month"].cut([0, 2, 5, 7, 10, 12], ["Winter", "Spring", "Summer", "Autumn", "Winter"])
def insert_missing(ip,port):
air_path = [h2o.locate("smalldata/airlines/allyears2k_headers.zip")]
data = h2o.import_file(path=air_path)
hour1 = data["CRSArrTime"] / 100
mins1 = data["CRSArrTime"] % 100
arrTime = hour1*60 + mins1
hour2 = data["CRSDepTime"] / 100
mins2 = data["CRSDepTime"] % 100
depTime = hour2*60 + mins2
data["TravelTime"] = h2o.ifelse((arrTime-depTime)>0,(arrTime-depTime),float("nan"))[0]
data.show()
def refine_date_col(data, col, pattern):
data[col] = data[col].as_date(pattern)
data["Day"] = data[col].day()
data["Month"] = data[col].month() + 1 # Since H2O indexes from 0
data["Year"] = data[col].year() + 1900 # Start of epoch is 1900
data["WeekNum"] = data[col].week()
data["WeekDay"] = data[col].dayOfWeek()
data["HourOfDay"] = data[col].hour()
data.describe(
) # HACK to force evaluation before the ifelse and cut... basically current execution scheme with Expr is way too restrictive and is going away soon. so we need hacks like this to circumvent type issues and the like
# Create weekend and season cols
# Spring = Mar, Apr, May. Summer = Jun, Jul, Aug. Autumn = Sep, Oct. Winter = Nov, Dec, Jan, Feb.
# data["Weekend"] = [1 if x in ("Sun", "Sat") else 0 for x in data["WeekDay"]]
data["Weekend"] = h2o.ifelse(
data["WeekDay"] == "Sun" or data["WeekDay"] == "Sat", 1, 0)[0]
data["Season"] = data["Month"].cut(
[0, 2, 5, 7, 10, 12],
["Winter", "Spring", "Summer", "Autumn", "Winter"])