def main():
train, test = u.get_train_test_df()
user_events_dict = u.get_user_events_dict(test)
for user in sorted(user_events_dict):
random.shuffle(user_events_dict[user])
u.write_submission("random_benchmark.csv", user_events_dict)
def main():
train, test = u.get_train_test_df()
user_events_dict = u.get_user_events_dict(test)
event_attendees = u.get_event_attendees()
event_yes = u.get_event_responses_dict(event_attendees["event"], event_attendees["yes"])
for user in user_events_dict:
user_events_dict[user] = sorted(user_events_dict[user],
key=lambda e: len(event_yes[e]), reverse=True)
u.write_submission("event_popularity_benchmark.csv", user_events_dict)
def clean_df():
train, test = util.get_train_test_df()
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
for col in columns:
if train[col].dtype == np.dtype('object'):
s = np.unique(train[col].fillna(-1).values)
mapping = pd.Series([x[0] for x in enumerate(s)], index = s)
train_fea = train_fea.join(train[col].map(mapping).fillna(-1))
test_fea = test_fea.join(test[col].map(mapping).fillna(-1))
else:
train_fea = train_fea.join(train[col].fillna(0))
test_fea = test_fea.join(test[col].fillna(0))
train_fea = train_fea.join(train['SalePrice'])
return train_fea, test_fea
def preprocess1():
train, test = util.get_train_test_df()
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
for col in columns:
print col
types = set(type(x) for x in train[col])
if str in types:
print "in:", col
s = set(x for x in train[col])
str_to_categorical = defaultdict(lambda: -1, [(x[1], x[0]) for x in enumerate(s)])
#print str_to_categorical
#return
train_fea = train_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in train[col]]}, index=train.index))
test_fea = test_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in test[col]]}, index=test.index))
else:
train_fea = train_fea.join(train[col])
test_fea = test_fea.join(test[col])
train_fea.to_csv("train_fea.csv", index=False)
test_fea.to_csv("test_fea.csv", index=False)
train["SalePrice"].to_csv("target.csv", index=False)
train["SalesID"].to_csv("train_salesID.csv", index=False)
test["SalesID"].to_csv("test_salesID.csv", index=False)
def preprocess():
train, test = util.get_train_test_df()
columns = set(train.columns)
#columns.remove("SalesID")
#columns.remove("SalePrice")
#columns.remove("saledate")
#train_fea = get_date_dataframe(train["saledate"])
#test_fea = get_date_dataframe(test["saledate"])
#parseColumns = ["UsageBand"]
parseColumns = [ "UsageBand","fiBaseModel","fiModelSeries","fiModelDescriptor","ProductSize","ProductGroup","Drive_System","Enclosure","Forks","Pad_Type","Ride_Control","Stick","Transmission","Turbocharged","Blade_Extension","Blade_Width","Enclosure_Type","Engine_Horsepower","Hydraulics","Pushblock","Ripper","Scarifier","Tip_ControlCoupler","Coupler_System","Grouser_Tracks","Hydraulics_Flow","Track_Type","Thumb","Pattern_Changer","Grouser_Type","Backhoe_Mounting","Blade_Type","Travel_Controls","Differential_Type","Steering_Controls"]
#"auctioneerID","state","ProductGroupDesc",,"fiSecondaryDesc"
# this is redundant "fiModelDesc", and has too many options...
# Q, AC, AL AR AS
colDict = {}
for col in parseColumns:
colDict[col] = []
colMap = {}
notInTest = []
for index, col in enumerate(train.columns):
print "MAP:", col, index
colMap[col] = index
if col in parseColumns:
#print "start"
s = set(x for x in train[col].fillna(0)) # 0 if x == "" or not isinstance(x, float) else x
s.update(x for x in test[col].fillna(0)) # math.isnan(x)
colDict[col] = s
print s
if col == "fiBaseModel":
a = set(x for x in train[col].fillna(0))
b = set(x for x in test[col].fillna(0))
print "fiBaseModel"
print
print
# found 11 type in test not in train
print [x for x in b if x not in a]
print
print
# found several hundred in train that are not in test, try dropping these...
print [x for x in a if x not in b]
notInTest = [x for x in a if x not in b]
SaleIDArr = []
trainSalePriceArr = []
count = 0
csv_io.delete_file("train1.csv")
for row in train.iterrows():
trainSalePrice = []
rowVals = row[1].fillna(0)
newSet = []
newRow = []
if rowVals["fiBaseModel"] not in notInTest:
continue
trainSalePrice.append(rowVals["SalePrice"])
trainSalePriceArr.append(trainSalePrice)
SaleID = []
SaleID.append(rowVals["SalesID"])
SaleIDArr.append(SaleID)
for col in colDict.keys():
for val in colDict[col]:
if val == rowVals[col] :
newRow.append(1)
else:
newRow.append(0)
#newRow.append(rowVals["YearMade"]) # need to calculate age, sale date minus year
newRow.append(rowVals["MachineHoursCurrentMeter"])
count += 1
if count % 10000 == 0:
print "Count", count
newSet.append(newRow)
csv_io.write_delimited_file("train1.csv", newSet ,header=None, delimiter=",", filemode="a")
csv_io.write_delimited_file("target.csv", trainSalePriceArr ,header=None, delimiter=",")
csv_io.write_delimited_file("train_salesID.csv", SaleIDArr ,header=None, delimiter=",")
# -------------------------------------------
SaleIDArr = []
count = 0
csv_io.delete_file("test1.csv")
for row in test.iterrows():
rowVals = row[1].fillna(0)
newSet = []
newRow = []
SaleID = []
SaleID.append(rowVals["SalesID"])
SaleIDArr.append(SaleID)
for col in colDict.keys():
for val in colDict[col]:
if val == rowVals[col] :
newRow.append(1)
else:
newRow.append(0)
#newRow.append(rowVals["YearMade"]) # need to calculate age, sale date minus year
newRow.append(rowVals["MachineHoursCurrentMeter"])
count += 1
if count % 10000 == 0:
print "Count", count
newSet.append(newRow)
csv_io.write_delimited_file("test1.csv", newSet ,header=None, delimiter=",", filemode="a")
csv_io.write_delimited_file("test_salesID.csv", SaleIDArr ,header=None, delimiter=",")
if __name__=="__main__":
preprocess()
def preprocess():
train, test = util.get_train_test_df()
columns = set(train.columns)
#columns.remove("SalesID")
#columns.remove("SalePrice")
#columns.remove("saledate")
#train_fea = get_date_dataframe(train["saledate"])
#test_fea = get_date_dataframe(test["saledate"])
#parseColumns = ["UsageBand"]
parseColumns = [ "UsageBand","fiBaseModel","fiModelSeries","fiModelDescriptor","ProductSize","ProductGroup","Drive_System","Enclosure","Forks","Pad_Type","Ride_Control","Stick","Transmission","Turbocharged","Blade_Extension","Blade_Width","Enclosure_Type","Engine_Horsepower","Hydraulics","Pushblock","Ripper","Scarifier","Tip_ControlCoupler","Coupler_System","Grouser_Tracks","Hydraulics_Flow","Track_Type","Thumb","Pattern_Changer","Grouser_Type","Backhoe_Mounting","Blade_Type","Travel_Controls","Differential_Type","Steering_Controls"]
#"auctioneerID","state","ProductGroupDesc",,"fiSecondaryDesc"
# this is redundant "fiModelDesc", and has too many options...
# Q, AC, AL AR AS
colDict = {}
for col in parseColumns:
colDict[col] = []
colMap = {}
notInTest = []
for index, col in enumerate(train.columns):
print "MAP:", col, index
colMap[col] = index
if col in parseColumns:
#print "start"
s = set(x for x in train[col].fillna(0)) # 0 if x == "" or not isinstance(x, float) else x
s.update(x for x in test[col].fillna(0)) # math.isnan(x)
colDict[col] = s
print s
if col == "fiBaseModel":
a = set(x for x in train[col].fillna(0))
b = set(x for x in test[col].fillna(0))
print "fiBaseModel"
print
print
# found 11 type in test not in train
print [x for x in b if x not in a]
print
print
# found several hundred in train that are not in test, try dropping these...
print [x for x in a if x not in b]
notInTest = [x for x in a if x not in b]
SaleIDArr = []
trainSalePriceArr = []
count = 0
csv_io.delete_file("train1.csv")
for row in train.iterrows():
trainSalePrice = []
rowVals = row[1].fillna(0)
newSet = []
newRow = []
if rowVals["fiBaseModel"] not in notInTest:
continue
trainSalePrice.append(rowVals["SalePrice"])
trainSalePriceArr.append(trainSalePrice)
SaleID = []
SaleID.append(rowVals["SalesID"])
SaleIDArr.append(SaleID)
for col in colDict.keys():
for val in colDict[col]:
if val == rowVals[col] :
newRow.append(1)
else:
newRow.append(0)
#newRow.append(rowVals["YearMade"]) # need to calculate age, sale date minus year
newRow.append(rowVals["MachineHoursCurrentMeter"])
count += 1
if count % 10000 == 0:
print "Count", count
newSet.append(newRow)
csv_io.write_delimited_file("train1.csv", newSet ,header=None, delimiter=",", filemode="a")
csv_io.write_delimited_file("target.csv", trainSalePriceArr ,header=None, delimiter=",")
csv_io.write_delimited_file("train_salesID.csv", SaleIDArr ,header=None, delimiter=",")
# -------------------------------------------
SaleIDArr = []
count = 0
csv_io.delete_file("test1.csv")
for row in test.iterrows():
rowVals = row[1].fillna(0)
newSet = []
newRow = []
SaleID = []
SaleID.append(rowVals["SalesID"])
SaleIDArr.append(SaleID)
for col in colDict.keys():
for val in colDict[col]:
if val == rowVals[col] :
newRow.append(1)
else:
newRow.append(0)
#newRow.append(rowVals["YearMade"]) # need to calculate age, sale date minus year
newRow.append(rowVals["MachineHoursCurrentMeter"])
count += 1
if count % 10000 == 0:
print "Count", count
newSet.append(newRow)
csv_io.write_delimited_file("test1.csv", newSet ,header=None, delimiter=",", filemode="a")
csv_io.write_delimited_file("test_salesID.csv", SaleIDArr ,header=None, delimiter=",")
from collections import defaultdict
import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
import util
def get_date_dataframe(date_column):
return pd.DataFrame({
"SaleYear": [d.year for d in date_column],
"SaleMonth": [d.month for d in date_column],
"SaleDay": [d.day for d in date_column]
}, index=date_column.index)
train, test = util.get_train_test_df()
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
for col in columns:
types = set(type(x) for x in train[col])
if str in types:
s = set(x for x in train[col])
str_to_categorical = defaultdict(lambda: -1, [(x[1], x[0]) for x in enumerate(s)])
train_fea = train_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in train[col]]}, index=train.index))
test_fea = test_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in test[col]]}, index=test.index))
else:
def data_to_fea():
"""Main preprocessing"""
train, test = util.get_train_test_df()
if testing == 1:
# This is the to test predict
test = train[(train["saledate"] >= datetime.datetime(2011,1,1)) & (train["saledate"] < datetime.datetime(2011,5,1))]
test = test.reset_index(drop = True)
test_Y = test["SalePrice"]
train = train[(train["saledate"] < datetime.datetime(2011,1,1))]
train = train.reset_index(drop = True) # drops the original index
del test["SalePrice"]
print 'test shape', test.shape
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
train_fea = map_external_data( train_fea)
test_fea = map_external_data(test_fea)
print "Cleaning Columns"
train, train_fea = clean_columns(train, train_fea)
test, test_fea = clean_columns(test, test_fea)
# train[["power_min", "power_max", "SalePrice", "ProductGroup", "YearMade"]].to_csv('power_min_out.csv', index=True)
test_columns = set(test.columns)
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
for col in columns:
# these deleted already["ProductGroupDesc", "fiProductClassDesc"]
if col not in col_list : # REAL ONE
#if col == "fiBaseModel":
# col_list = ["ProductSize","UsageBand",'fiProductClassDesc'] # "ProductGroup"
#if col == "Backhoe_Mounting": # Testing - error in the fillna "convert string to float" but why?
#print "starting", col
# find newest. populates fiSecondaryDesc
# Need to fix so that train_fea returns SaleYear
#if col == 'fiBaseModel':
# train_fea = newest_model(train)
# test_fea = newest_model(test)
# Binarize these, even if numerical
if col in [ 'ProductGroup', 'state','fiModelSeries','fiModelDescriptor',
'auctioneerID', 'power_u', 'MfgID', 'Enclosure', 'SaleDay', "SaleWkDay", "fiProductClassDesc"] :
print "binarize", col
if col in ['auctioneerID', 'MfgID']:
train[col]=train[col].fillna(value =0)
test[col] = test[col].fillna(value = 0)
else:
train[col]=train[col].fillna(value ="")
test[col] = test[col].fillna(value = "")
s = np.unique(x for x in np.append(train[col].values,test[col].values))
#print col, ":", len(s), ":",s[:10]
# would binarize BaseModel but too much memory
train_fea, test_fea = binarize_cols(col, train, test, train_fea, test_fea)
elif train[col].dtype == np.dtype('object') and col not in ['power_min', 'power_max']:
#print "filling na"
train[col]=train[col].fillna(value ="")
test[col] = test[col].fillna(value = "")
#
s = np.unique(x for x in np.append(train[col].values,test[col].values))
#print col, ":", len(s), ":", s[:10]
# Binarize these ones:
if len(s) >2 and len(s) < 100 and col not in "Thumb": # in [ 'fiBaseModel']
# try on len(s) > 3
# don't binarize datasource (6 values), lower performance
#print "binarize", col
# would binarize BaseModel but too much memory
train_fea, test_fea = binarize_cols(col, train, test, train_fea, test_fea)
# Just enumerate these
else:
#if 1:
#print "enumerate",col
#Don't need below line for full data set usually
if test[col].dtype != np.dtype(object):
test[col] = test[col].astype(object) # in case test had diff type
if len(s) == 2:
# assume one is ""
# one replace function would have been able to do this
new_arr_train = []
new_arr_test = []
for x in train[col]:
repl = 0 if x == "" else 1
new_arr_train.append(repl)
for x in test[col]:
repl = 0 if x == "" else 1
new_arr_test.append(repl)
train_fea[col] = new_arr_train
test_fea[col] = new_arr_test
else:
# Regular dumb indexing
mapping = pd.Series([x[0] for x in enumerate(s)], index = s) # Original code
train_fea[col] = train[col].map(mapping)
test_fea[col] = test[col].map(mapping)
#train_fea[col] = np.log(train_fea[col]+1)
#test_fea[col] = np.log(test_fea[col]+1)
if pd.isnull(train_fea[col]).any() or pd.isnull(test_fea[col]).any():
print "HAS NAN", col
else:
# Numeric field
#print col, " as number"
#if train[col].dtype != np.dtype('object'):
#m = np.mean([x for x in train[col] if not np.isnan(x)])
# can use pd.isnull(frame).any() TRY
if col =="MachineID" or col == "ModelID" or col == "datasource":
m = 0 # value to fill
train_m = 0
test_m = 0
elif col in [ "MachineHoursCurrentMeter", 'Stick_Length']:
# Diff w/ 0 is not large
train_m = round(np.mean([x for x in train[col] if x > 0]),1)
test_m = round(np.mean([x for x in test[col] if x > 0]),1)
#elif col == "Stick_Length":
#train_m = round(np.median([x for x in train[col] if x > 0]),1)
#test_m = round(np.median([x for x in test[col] if x > 0]),1)
else:
# Calculate median, better oob performance than mean
train_m= np.median(train[col]) # if x > 0?
test_m= np.median(test[col])
#print m
#if col == 'power_min':
# train[col] = train[col].fillna(value =0)
# test[col] = test[col].fillna(value=0)
if col in ["Stick_Length"]:
train[col] = train[col].replace(0,train_m)
test[col] = test[col].replace(0,test_m)
else:
train[col] = train[col].fillna(value =train_m)
test[col] = test[col].fillna(value=test_m)
#print col, train_m
# "mean is nan"
if np.isnan(train_m): train[col] = train[col].fillna(value =0)
if np.isnan(test_m):test[col] = test[col].fillna(value=0)
#train[col] = train[col].astype('float64')
#test[col] = test[col].astype('float64')
train[col] = np.log(train[col]+1)
test[col] = np.log(test[col]+1)
train_fea[col] = train[col]
test_fea[col] = test[col]
#if col != "power_min":
# del train[col]
# del test[col]
#train_fea = train_fea.join(train[col])
#test_fea = test_fea.join(test[col])
if pd.isnull(train_fea[col]).any() or pd.isnull(test_fea[col]).any():
print "HAS NAN", col
#except:
#print "Error with col", col
#train_fea = train_fea[train_fea["SaleYear"] < 2011] # try this out # now at the top
#train = train[train["saledate"] <= datetime.datetime(2011,1,1)] # try this out # now at the top
del train_fea["SaleYear"]
del test_fea["SaleYear"]
if testing == 0:
return train_fea, test_fea, [x for x in train["SalePrice"]]
else:
return train_fea, test_fea, [x for x in train["SalePrice"]], test_Y
def main():
train, test = u.get_train_test_df()
user_events_dict = u.get_user_events_dict(test)
u.write_submission("given_order.csv", user_events_dict)
def run_stack(SEED):
train, test = util.get_train_test_df()
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
for col in columns:
types = set(type(x) for x in train[col])
if str in types:
s = set(x for x in train[col])
str_to_categorical = defaultdict(lambda: -1,
[(x[1], x[0])
for x in enumerate(s)])
train_fea = train_fea.join(
pd.DataFrame(
{col: [str_to_categorical[x] for x in train[col]]},
index=train.index))
test_fea = test_fea.join(
pd.DataFrame({col: [str_to_categorical[x] for x in test[col]]},
index=test.index))
else:
train_fea = train_fea.join(train[col])
test_fea = test_fea.join(test[col])
model = ""
print "Running Stack."
avg = 0
NumFolds = 5 # 5 is good, but 10 yeilds a better mean since outliers are less significant.
#targetX = csv_io.read_data("target.csv", skipFirstLine = False, split = ",")
#trainBase = csv_io.read_data("train1.csv", skipFirstLine = False, split = ",")
#test = csv_io_np.read_data("test1.csv", skipFirstLine = False, split = ",")
#trainBase = trainBase[0:5000]
#targetX = targetX[0:5000]
#train_saleID = csv_io.read_data("train_salesID.csv", skipFirstLine = False, split = ",")
#test_salesID = csv_io.read_data("test_salesID.csv", skipFirstLine = False, split = ",")
predicted_list = []
bootstrapLists = []
clfs = [
GradientBoostingRegressor(loss='lad',
learn_rate=0.05,
subsample=0.5,
max_depth=6,
n_estimators=3000,
random_state=166,
min_samples_leaf=1)
]
#GradientBoostingRegressor(loss='ls', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=300, random_state=166, min_samples_leaf=1)
#GradientBoostingRegressor(loss='lad', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=3000, random_state=166, min_samples_leaf=1),
#GradientBoostingRegressor(loss='huber', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=3000, random_state=166, min_samples_leaf=1),
#train_fea, train["SalePrice"]
print "Data size: ", len(train_fea), len(test_fea)
#dataset_blend_train = np.zeros((len(train_fea), len(clfs)))
#dataset_blend_test = np.zeros((len(test), len(clfs)))
dataset_blend_test = np.zeros(
(len(test_fea), len(clfs))) # np.zeros(len(train_fea), len(clfs))
dataset_blend_train = np.zeros((len(train_fea), len(clfs)))
print "Begin Training"
lenTrainBase = 401125 # len(train_fea)
lenTest = 11573 # len(test_fea)
gc.collect()
for ExecutionIndex, clf in enumerate(clfs):
print clf
avg = 0
predicted_list = []
dataset_blend_test_set = np.zeros((lenTest, NumFolds))
foldCount = 0
#Stratified for classification...[trainBase[i][0] for i in range(len(trainBase))]
Folds = cross_validation.KFold(lenTrainBase, k=NumFolds, indices=True)
for train_index, test_index in Folds:
targetX = [train["SalePrice"][i] for i in train_index]
trainX = [train_fea.ix[i] for i in train_index]
targetTest = [train["SalePrice"][i] for i in test_index]
trainTest = [train_fea.ix[i] for i in test_index]
gc.collect()
print
print "Iteration: ", foldCount
print "LEN: ", len(trainX), len(targetX)
#print trainX[0]
#print target[0]
#return
print "Start", datetime.datetime.now()
clf.fit(trainX, targetX)
prob = clf.predict(trainTest)
print "End ", datetime.datetime.now()
dataset_blend_train[test_index, ExecutionIndex] = prob
gc.collect()
probSum = 0
weightSum = 0
# totalOffByHalf = 0
# totalPositive = 0
# totalPositiveOffByHalf = 0
# totalPositivePredictions = 0
for i in range(0, len(prob)):
probX = prob[i]
#print targetTest[i], probX
if probX < 0: # some are comming out negative.
probX = -probX
probSum += math.pow(
math.log10(targetTest[i]) - math.log10(probX), 2)
#probSum += weights[test_index[i]][0] * math.fabs(targetTest[i] - probX)
#weightSum += weights[test_index[i]][0]
#print "Weight", weights[test_index[i]][0], "Index: ",i, "Test_Index: ",test_index[i] , "Actual: ", targetTest[i], "Predicted: ", probX
# log loss cal
#probSum += int(targetTest[i])*log(probX)+(1-int(targetTest[i]))*log(1-probX)
# if ( math.fabs(probX - int(targetTest[i])) > 0.5 ):
# totalOffByHalf = totalOffByHalf + 1
# if ( int(targetTest[i]) == 1 ):
# totalPositive = totalPositive + 1
# if ( int(targetTest[i]) == 1 and probX < 0.5):
# totalPositiveOffByHalf = totalPositiveOffByHalf + 1
# if (probX > 0.5):
# totalPositivePredictions = totalPositivePredictions + 1
# print
# print "Stats:"
# print "Total Off By > 0.5 ", totalOffByHalf
# print "Total Positive ", totalPositive
# print "Total Positive Off By Half ", totalPositiveOffByHalf
# print "Total Positive Predictions ", totalPositivePredictions
#print -probSum/len(prob)
print "Score: ", math.sqrt(probSum / len(prob))
avg += math.sqrt(probSum / len(prob)) / NumFolds
gc.collect()
predicted_probs = []
for i in range(0, lenTest):
predicted_probs.append(clf.predict(test_fea.ix[i]))
#predicted_probs = clf.predict(testScaled)
#predicted_list.append([x[1] for x in predicted_probs])
dataset_blend_test_set[:, foldCount] = predicted_probs #[0]
gc.collect()
foldCount = foldCount + 1
dataset_blend_test[:, ExecutionIndex] = dataset_blend_test_set.mean(1)
#print "Saving NP"
#np.savetxt('temp/dataset_blend_test_set.txt', dataset_blend_test_set)
#np.savetxt('temp/dataset_blend_test_set.mean.txt', dataset_blend_test_set.mean(1) )
#np.savetxt('temp/dataset_blend_test.txt', dataset_blend_test)
#print "Done Saving NP"
now = datetime.datetime.now()
#print dataset_blend_test_set.mean(1)
csv_io.write_delimited_file_single(
"../predictions/Stack_" + now.strftime("%Y%m%d%H%M%S") + "_" +
str(avg) + "_" + str(clf)[:12] + ".csv",
dataset_blend_test_set.mean(1))
csv_io.write_delimited_file_single(
"../predictions/Target_Stack_" + now.strftime("%Y%m%d%H%M%S") +
"_" + str(avg) + "_" + str(clf)[:12] + ".csv",
dataset_blend_train[:, ExecutionIndex])
csv_io.write_delimited_file("../predictions/RunLog.csv", [
now.strftime("%Y %m %d %H %M %S"), "AVG.",
str(avg),
str(clf), "Folds:",
str(NumFolds), "Model", model, "", ""
],
filemode="a",
delimiter=",")
print "------------------------Average: ", avg
#np.savetxt('temp/dataset_blend_train.txt', dataset_blend_train)
return dataset_blend_train, dataset_blend_test
import numpy as np
import pandas as pd
import util
train, test = util.get_train_test_df()
median_price = np.median(train["SalePrice"])
print("The median price is %0.2f" % median_price)
util.write_submission("median_benchmark.csv",
[median_price for i in range(len(test))])
def main():
train, test = u.get_train_test_df()
user_events_dict = u.get_user_events_dict(test)
u.write_submission("given_order.csv", user_events_dict)
def run_stack(SEED):
train, test = util.get_train_test_df()
columns = set(train.columns)
columns.remove("SalesID")
columns.remove("SalePrice")
columns.remove("saledate")
train_fea = get_date_dataframe(train["saledate"])
test_fea = get_date_dataframe(test["saledate"])
for col in columns:
types = set(type(x) for x in train[col])
if str in types:
s = set(x for x in train[col])
str_to_categorical = defaultdict(lambda: -1, [(x[1], x[0]) for x in enumerate(s)])
train_fea = train_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in train[col]]}, index=train.index))
test_fea = test_fea.join(pd.DataFrame({col: [str_to_categorical[x] for x in test[col]]}, index=test.index))
else:
train_fea = train_fea.join(train[col])
test_fea = test_fea.join(test[col])
model = ""
print "Running Stack."
avg = 0
NumFolds = 5 # 5 is good, but 10 yeilds a better mean since outliers are less significant.
#targetX = csv_io.read_data("target.csv", skipFirstLine = False, split = ",")
#trainBase = csv_io.read_data("train1.csv", skipFirstLine = False, split = ",")
#test = csv_io_np.read_data("test1.csv", skipFirstLine = False, split = ",")
#trainBase = trainBase[0:5000]
#targetX = targetX[0:5000]
#train_saleID = csv_io.read_data("train_salesID.csv", skipFirstLine = False, split = ",")
#test_salesID = csv_io.read_data("test_salesID.csv", skipFirstLine = False, split = ",")
predicted_list = []
bootstrapLists = []
clfs = [
GradientBoostingRegressor(loss='lad', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=3000, random_state=166, min_samples_leaf=1)
]
#GradientBoostingRegressor(loss='ls', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=300, random_state=166, min_samples_leaf=1)
#GradientBoostingRegressor(loss='lad', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=3000, random_state=166, min_samples_leaf=1),
#GradientBoostingRegressor(loss='huber', learn_rate=0.05, subsample=0.5, max_depth=6, n_estimators=3000, random_state=166, min_samples_leaf=1),
#train_fea, train["SalePrice"]
print "Data size: ", len(train_fea) , len(test_fea)
#dataset_blend_train = np.zeros((len(train_fea), len(clfs)))
#dataset_blend_test = np.zeros((len(test), len(clfs)))
dataset_blend_test = np.zeros((len(test_fea), len(clfs))) # np.zeros(len(train_fea), len(clfs))
dataset_blend_train = np.zeros((len(train_fea), len(clfs)))
print "Begin Training"
lenTrainBase = 401125 # len(train_fea)
lenTest = 11573 # len(test_fea)
gc.collect()
for ExecutionIndex, clf in enumerate(clfs):
print clf
avg = 0
predicted_list = []
dataset_blend_test_set = np.zeros((lenTest, NumFolds))
foldCount = 0
#Stratified for classification...[trainBase[i][0] for i in range(len(trainBase))]
Folds = cross_validation.KFold(lenTrainBase, k=NumFolds, indices=True)
for train_index, test_index in Folds:
targetX = [train["SalePrice"][i] for i in train_index]
trainX = [train_fea.ix[i] for i in train_index]
targetTest = [train["SalePrice"][i] for i in test_index]
trainTest = [train_fea.ix[i] for i in test_index]
gc.collect()
print
print "Iteration: ", foldCount
print "LEN: ", len(trainX), len(targetX)
#print trainX[0]
#print target[0]
#return
print "Start", datetime.datetime.now()
clf.fit(trainX, targetX)
prob = clf.predict(trainTest)
print "End ", datetime.datetime.now()
dataset_blend_train[test_index, ExecutionIndex] = prob
gc.collect()
probSum = 0
weightSum = 0
# totalOffByHalf = 0
# totalPositive = 0
# totalPositiveOffByHalf = 0
# totalPositivePredictions = 0
for i in range(0, len(prob)):
probX = prob[i]
#print targetTest[i], probX
if probX < 0: # some are comming out negative.
probX = -probX
probSum += math.pow(math.log10(targetTest[i]) - math.log10(probX), 2)
#probSum += weights[test_index[i]][0] * math.fabs(targetTest[i] - probX)
#weightSum += weights[test_index[i]][0]
#print "Weight", weights[test_index[i]][0], "Index: ",i, "Test_Index: ",test_index[i] , "Actual: ", targetTest[i], "Predicted: ", probX
# log loss cal
#probSum += int(targetTest[i])*log(probX)+(1-int(targetTest[i]))*log(1-probX)
# if ( math.fabs(probX - int(targetTest[i])) > 0.5 ):
# totalOffByHalf = totalOffByHalf + 1
# if ( int(targetTest[i]) == 1 ):
# totalPositive = totalPositive + 1
# if ( int(targetTest[i]) == 1 and probX < 0.5):
# totalPositiveOffByHalf = totalPositiveOffByHalf + 1
# if (probX > 0.5):
# totalPositivePredictions = totalPositivePredictions + 1
# print
# print "Stats:"
# print "Total Off By > 0.5 ", totalOffByHalf
# print "Total Positive ", totalPositive
# print "Total Positive Off By Half ", totalPositiveOffByHalf
# print "Total Positive Predictions ", totalPositivePredictions
#print -probSum/len(prob)
print "Score: ", math.sqrt(probSum/len(prob))
avg += math.sqrt(probSum/len(prob))/NumFolds
gc.collect()
predicted_probs = []
for i in range(0,lenTest):
predicted_probs.append(clf.predict(test_fea.ix[i]))
#predicted_probs = clf.predict(testScaled)
#predicted_list.append([x[1] for x in predicted_probs])
dataset_blend_test_set[:, foldCount] = predicted_probs #[0]
gc.collect()
foldCount = foldCount + 1
dataset_blend_test[:,ExecutionIndex] = dataset_blend_test_set.mean(1)
#print "Saving NP"
#np.savetxt('temp/dataset_blend_test_set.txt', dataset_blend_test_set)
#np.savetxt('temp/dataset_blend_test_set.mean.txt', dataset_blend_test_set.mean(1) )
#np.savetxt('temp/dataset_blend_test.txt', dataset_blend_test)
#print "Done Saving NP"
now = datetime.datetime.now()
#print dataset_blend_test_set.mean(1)
csv_io.write_delimited_file_single("../predictions/Stack_" + now.strftime("%Y%m%d%H%M%S") + "_" + str(avg) + "_" + str(clf)[:12] + ".csv", dataset_blend_test_set.mean(1))
csv_io.write_delimited_file_single("../predictions/Target_Stack_" + now.strftime("%Y%m%d%H%M%S") + "_" + str(avg) + "_" + str(clf)[:12] + ".csv", dataset_blend_train[:,ExecutionIndex] )
csv_io.write_delimited_file("../predictions/RunLog.csv", [now.strftime("%Y %m %d %H %M %S"), "AVG." , str(avg), str(clf), "Folds:", str(NumFolds), "Model", model, "", ""], filemode="a",delimiter=",")
print "------------------------Average: ", avg
#np.savetxt('temp/dataset_blend_train.txt', dataset_blend_train)
return dataset_blend_train, dataset_blend_test
import util as u
import pandas as pd
import operator
import numpy as np
from sklearn import ensemble, cross_validation, metrics
import re
## todo: gradient boosted model?
if __name__ == '__main__':
train, test = u.get_train_test_df(test_set=False)
## define columns to use for features
## not used: SalesID, MachineID, ModelID, Saledate, fiModelDesc
## ProductClassDesc, ProductGroupDesk
## fiBaseModel, fiSecondaryDesc, fiModelSeries, fiModelDescriptor
categorical = {'datasource', 'auctioneerID', 'UsageBand', 'ProductSize', 'ProductGroup', 'Drive_System',
'Enclosure', 'Forks', 'Pad_Type', 'Ride_Control', 'Stick', 'Transmission', 'Turbocharged', 'Blade_Extension',
'Blade_Width', 'Enclosure_Type', 'Engine_Horsepower', 'Hydraulics', 'Pushblock', 'Ripper', 'Scarifier',
'Tip_Control', 'Tire_Size', 'Coupler', 'Coupler_System', 'Grouser_Tracks', 'Hydraulics_Flow', 'Track_Type',
'Thumb', 'Pattern_Changer', 'Grouser_Type', 'Backhoe_Mounting', 'Blade_Type', 'Travel_Controls',
'Differential_Type', 'Steering_Controls'}
numerical = {'YearMade', 'MachineHoursCurrentMeter', 'Undercarriage_Pad_Width', 'Stick_Length'}
def get_date_dataframe(date_column):
'''Create a data frame with columns for each date constituent'''
return pd.DataFrame({
'SaleYear' : [d.year for d in date_column],
'SaleMonth' : [d.month for d in date_column],
