Python AllStatePredictor示例

示例#1

文件： submission_linearsvc.py 项目： ageek/AllStateKaggle

import os
import sys
import pandas as pd
sys.path.append("lib")

from AllStatePredictor import AllStatePredictor

p = AllStatePredictor()

def concat_ABCDEFG(x):
    return "%d%d%d%d%d%d%d" % (x['A'], x['B'], x['C'], x['D'], x['E'], x['F'], x['G'])

print "prediction classe 2 linear svc..."
customer_ID_list_2 = p.get_customer_ID_list("2")
a_prediction_2 = p.predict("A", "linearsvc", "not_centered", "2")
b_prediction_2 = p.predict("B", "linearsvc", "not_centered", "2")
c_prediction_2 = p.predict("C", "linearsvc", "not_centered", "2")
d_prediction_2 = p.predict("D", "linearsvc", "not_centered", "2")
e_prediction_2 = p.predict("E", "linearsvc", "not_centered", "2")
f_prediction_2 = p.predict("F", "linearsvc", "not_centered", "2")
g_prediction_2 = p.predict("G", "linearsvc", "not_centered", "2")

prediction_2_detail = pd.DataFrame(
    {
        'A' : a_prediction_2,
        'B' : b_prediction_2,
        'C' : c_prediction_2,
        'D' : d_prediction_2,
        'E' : e_prediction_2,
        'F' : f_prediction_2,
        'G' : g_prediction_2

示例#2

文件： predict_ABCDEFG_train_extratrees_cascade.py 项目： ageek/AllStateKaggle

from AllStateDataLoader import AllStateDataLoader
from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np


def score(y_predict, y_real):
    n = float(y_predict.shape[0])

    n_ok = float(np.sum(y_predict == y_real))

    return (n_ok/n)

l = AllStateDataLoader()
p = AllStatePredictor()

# X_2 = l.get_X_train("2", "")
y_2 = l.get_y("2", "ABCDEFG")
y_2_predict = p.predict_cascade("2", "extratrees", "ABCDEFG", kind="train")

# X_3 = l.get_X_train("3", "")
y_3 = l.get_y("3", "ABCDEFG")
y_3_predict = p.predict_cascade("3", "extratrees", "ABCDEFG", kind="train")

# X_4 = l.get_X_train("4", "")
y_4 = l.get_y("4", "ABCDEFG")
y_4_predict = p.predict_cascade("4", "extratrees", "ABCDEFG", kind="train")

# X_all = l.get_X_train("all", "")
y_all = l.get_y("all", "ABCDEFG")

示例#3

import sys
sys.path.append("lib")

from AllStateDataLoader import AllStateDataLoader
from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np
import pandas as pd

p = AllStatePredictor()

y_2_predict = p.predict_simple("2", "extratrees", "ABCDEFG", kind="test")
y_3_predict = p.predict_simple("3", "extratrees", "ABCDEFG", kind="test")
y_4_predict = p.predict_simple("4", "extratrees", "ABCDEFG", kind="test")
y_all_predict = p.predict_simple("all", "extratrees", "ABCDEFG", kind="test")

y_submission = y_2_predict.append([y_3_predict, y_4_predict, y_all_predict])

y_submission = y_submission.sort_index()

df = pd.DataFrame(data={'plan': y_submission}, index=y_submission.index)

df.to_csv("extratrees_simple_sans_location.csv")

示例#4

import sys
sys.path.append("lib")

from AllStateDataLoader import AllStateDataLoader
from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np
import pandas as pd

p = AllStatePredictor()

y_2_predict = p.predict_simple("2", "linearsvc", "ABCDEFG", kind="test")
y_3_predict = p.predict_simple("3", "linearsvc", "ABCDEFG", kind="test")
y_4_predict = p.predict_simple("4", "linearsvc", "ABCDEFG", kind="test")
y_all_predict = p.predict_simple("all", "linearsvc", "ABCDEFG", kind="test")

y_submission = y_2_predict.append([
    y_3_predict,
    y_4_predict,
    y_all_predict
])

y_submission = y_submission.sort_index()

df = pd.DataFrame(data={'plan':y_submission}, index=y_submission.index)

df.to_csv("linearsvc_simple_sans_location.csv")

示例#5

文件： predict_ABCDEFG_train_linearsvc_cascade.py 项目： ageek/AllStateKaggle

from AllStateDataLoader import AllStateDataLoader
from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np


def score(y_predict, y_real):
    n = float(y_predict.shape[0])

    n_ok = float(np.sum(y_predict == y_real))

    return (n_ok/n)

l = AllStateDataLoader()
p = AllStatePredictor()

# X_2 = l.get_X_train("2", "")
y_2 = l.get_y("2", "ABCDEFG")
y_2_predict = p.predict_cascade("2", "linearsvc", "ABCDEFG", kind="train")

# X_3 = l.get_X_train("3", "")
y_3 = l.get_y("3", "ABCDEFG")
y_3_predict = p.predict_cascade("3", "linearsvc", "ABCDEFG", kind="train")

# X_4 = l.get_X_train("4", "")
y_4 = l.get_y("4", "ABCDEFG")
y_4_predict = p.predict_cascade("4", "linearsvc", "ABCDEFG", kind="train")

# X_all = l.get_X_train("all", "")
y_all = l.get_y("all", "ABCDEFG")

示例#6

import os
import sys
import pandas as pd
sys.path.append("lib")

from AllStatePredictor import AllStatePredictor

p = AllStatePredictor()


def concat_ABCDEFG(x):
    return "%d%d%d%d%d%d%d" % (x['A'], x['B'], x['C'], x['D'], x['E'], x['F'],
                               x['G'])


print "prediction classe 2 linear svc..."
customer_ID_list_2 = p.get_customer_ID_list("2")
a_prediction_2 = p.predict("A", "logistic", "not_centered", "2")
b_prediction_2 = p.predict("B", "logistic", "not_centered", "2")
c_prediction_2 = p.predict("C", "logistic", "not_centered", "2")
d_prediction_2 = p.predict("D", "logistic", "not_centered", "2")
e_prediction_2 = p.predict("E", "logistic", "not_centered", "2")
f_prediction_2 = p.predict("F", "logistic", "not_centered", "2")
g_prediction_2 = p.predict("G", "logistic", "not_centered", "2")

prediction_2_detail = pd.DataFrame(
    {
        'A': a_prediction_2,
        'B': b_prediction_2,
        'C': c_prediction_2,
        'D': d_prediction_2,

示例#7

文件： predict_ABCDEFG_test_extratrees_simple.py 项目： ageek/AllStateKaggle

import sys
sys.path.append("lib")

from AllStateDataLoader import AllStateDataLoader
from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np
import pandas as pd

p = AllStatePredictor()

y_2_predict = p.predict_simple("2", "extratrees", "ABCDEFG", kind="test")
y_3_predict = p.predict_simple("3", "extratrees", "ABCDEFG", kind="test")
y_4_predict = p.predict_simple("4", "extratrees", "ABCDEFG", kind="test")
y_all_predict = p.predict_simple("all", "extratrees", "ABCDEFG", kind="test")

y_submission = y_2_predict.append([
    y_3_predict,
    y_4_predict,
    y_all_predict
])

y_submission = y_submission.sort_index()

df = pd.DataFrame(data={'plan':y_submission}, index=y_submission.index)

df.to_csv("extratrees_simple_sans_location.csv")

示例#8

文件： predict_ABCDEFG_train_linearsvc_cascade.py 项目： mithunmanohar/kaggle

from AllStatePredictor import AllStatePredictor
from sklearn import linear_model
from sklearn import grid_search
import numpy as np


def score(y_predict, y_real):
    n = float(y_predict.shape[0])

    n_ok = float(np.sum(y_predict == y_real))

    return (n_ok / n)


l = AllStateDataLoader()
p = AllStatePredictor()

# X_2 = l.get_X_train("2", "")
y_2 = l.get_y("2", "ABCDEFG")
y_2_predict = p.predict_cascade("2", "linearsvc", "ABCDEFG", kind="train")

# X_3 = l.get_X_train("3", "")
y_3 = l.get_y("3", "ABCDEFG")
y_3_predict = p.predict_cascade("3", "linearsvc", "ABCDEFG", kind="train")

# X_4 = l.get_X_train("4", "")
y_4 = l.get_y("4", "ABCDEFG")
y_4_predict = p.predict_cascade("4", "linearsvc", "ABCDEFG", kind="train")

# X_all = l.get_X_train("all", "")
y_all = l.get_y("all", "ABCDEFG")