Last active
August 13, 2019 08:38
-
-
Save yankov/1ab961c108613cf2d63a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Avazu CTR prediction | |
# SGD Logistic regression + hashing trick. | |
import pandas as pd | |
import numpy as np | |
from datetime import datetime, date, time | |
from sklearn.linear_model import SGDClassifier | |
from sklearn.feature_extraction import FeatureHasher | |
from sklearn.preprocessing import LabelEncoder | |
cols = ["C1","banner_pos","site_category", "device_type","device_conn_type","C14","C15","C16","C17","C18","C19","C20","C21", "hour"] | |
# add two columns for hour and weekday | |
def dayhour(timestr): | |
d = datetime.strptime(str(x), "%y%m%d%H") | |
return [float(d.weekday()), float(d.hour)] | |
fh = FeatureHasher(n_features = 2**20, input_type="string") | |
# Train classifier | |
clf = SGDClassifier(loss="log", n_iter=1) | |
train = pd.read_csv("train", chunksize = 1000000, iterator = True) | |
all_classes = np.array([0, 1]) | |
for chunk in train: | |
y_train = chunk["click"] | |
chunk = chunk[cols] | |
chunk = chunk.join(pd.DataFrame([dayhour(x) for x in chunk.hour], columns=["wd", "hr"])) | |
chunk.drop("hour", axis=1, inplace = True) | |
Xcat = fh.transform(np.asarray(chunk.astype(str))) | |
clf.partial_fit(Xcat, y_train, classes=all_classes) | |
# Create a submission file | |
X_test = pd.read_csv("test", usecols = cols + ["id"]) | |
X_test = X_test.join(pd.DataFrame([dayhour(x) for x in X_test.hour], columns=["wd", "hr"])) | |
X_test.drop("hour", axis=1, inplace = True) | |
X_enc_test = fh.transform(np.asarray(X_test.astype(str))) | |
y_pred = clf.predict_proba(X_enc_test)[:, 1] | |
with open("submission.csv", "w") as f: | |
f.write("id,click\n") | |
for idx, xid in enumerate(X_test.id): | |
f.write(str(xid) + "," + "{0:.10f}".format(y_pred[idx]) + "\n") | |
f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment