資源簡介
天池大賽第六名。這個賽題不是典型的分類、聚類問題，而是時間序列問題，這種時間序列問題，主要在于學習出周期性和趨勢。為了達到學出周期性和趨勢的目標，可以試用統計學中典型的時間序列模型如STL分解和ARIMA，這樣的模型的優點是便捷，弱點是像個黑盒，不太便于添加更多特征。
代碼片段和文件信息
##########################?fit?##################################################
import?csv
import?math
import?numpy?as?np
import?pandas?as?pd
import?matplotlib.pyplot?as?pltf
from?sklearn.linear_model?import?Ridge
from?sklearn.preprocessing?import?PolynomialFeatures
from?sklearn.pipeline?import?make_pipeline
import?statsmodels.api?as?sm
from?statsmodels.tsa.arima_model?import?ARIMA
from?pp?import?*
def?fitJA（j?start_date_rank）:
????pltf.clf（）
????p?=?artists_play_inday[j]
????p?=?p[start_date_rank:]
????print?p
????apcount?=?[0]?*?（183?-?start_date_rank）
????apdate?=?range（start_date_rank?183）
????for?i?in?p:
????????apcount[i[1]?-?start_date_rank]?=?i[0]
????print?apcount
????d_train?=?np.asarray（apdate）
????c_train?=?np.asarray（apcount）
????#?create?matrix?versions?of?these?arrays
????D_train?=?d_train[:?np.newaxis]
????d_test_plot?=?np.asarray（range（start_date_rank?244））
????D_test_plot?=?d_test_plot[:?np.newaxis]
????pltf.scatter（d_train?c_train?label=“training?points“）
????for?degree?in?[123]:
????????model?=?make_pipeline（PolynomialFeatures（degree）?Ridge（））
????????model.fit（D_train?c_train）
????????c_test_plot?=?model.predict（D_test_plot）
????????pltf.plot（d_test_plot?c_test_plot?label=“degree?%d“?%?degree）
????pltf.legend（bbox_to_anchor=（0.?1.02?1.?.102）?loc=3?ncol=5?mode=“expand“?borderaxespad=0.）
????pltf.show（）
def?test（degree）:
????error_rate_of_artist?=?[]
????weight_of_artist?=?[]
????f_of_artist?=?[]
????F?=?0.0
????for?j?in?range（0?50）:
????????p?=?artists_play_inday[j]
????????apcount?=?[0]?*?184
????????apdate?=?range（0?184）
????????for?i?in?p:
????????????apcount[i[1]]?=?i[0]
????????x?=?np.asarray（apdate[:122]）
????????x_test?=?np.asarray（apdate[122:]）
????????X?=?x[:?np.newaxis]
????????y?=?np.asarray（apcount[:122]）
????????y_test_true?=?np.asarray（apcount[122:]）
????????X_test?=?x_test[:?np.newaxis]
????????model?=?make_pipeline（PolynomialFeatures（degree）?Ridge（））
????????model.fit（X?y）
????????y_test_pred?=?model.predict（X_test）
????????error_rate_pow2_sum?=?0.0
????????weight?=?0.0
????????for?idx?in?range（0?len（x_test））:
????????????y_true?=?y_test_true[idx]
????????????if?y_true?==?0:
????????????????y_true?=?1?#?deal?with?divide?by?zero
????????????error_rate_pow2_sum?+=?（float（（int（math.ceil（y_test_pred[idx]））?-?y_true））?/?float（y_true）?）**2
????????????weight?+=?y_test_true[idx]
????????error_rate_j?=?math.sqrt（error_rate_pow2_sum?/?float（len（x_test）））
????????error_rate_of_artist.append（error_rate_j）
????????weight_j?=?math.sqrt（weight）
????????weight_of_artist.append（weight_j）
????????f_j?=?（1?-?error_rate_j）?*?weight_j
????????f_of_artist.append（f_j）
????????F?+=?f_j
????print?‘degree‘?degree
????print?‘error_rate_of_artist‘?error_rate_of_artist
????print?‘weight_of_artist‘?weight_of_artist
????print?‘f_of_artist‘?f_of_artist
????print?‘F‘?F
def?pred（degree）:
????predict_file_path?=?“./data/mars_tianchi_artist_plays_predict.csv“
????fp?=?open（predict_file_path?‘?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\
?????文件??????????81??2016-06-19?14:09??AliMusicTrendPredict-master\.gitignore
?????文件???????12328??2016-06-19?14:09??AliMusicTrendPredict-master\F.png
?????文件???????16782??2016-06-19?14:09??AliMusicTrendPredict-master\README.md
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\
?????文件?????????562??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\0605_degreeOfEachArtist.txt
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\data\
?????文件???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\data\.placeholder
?????文件???????11334??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\le.py
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\pic\
?????文件??????149287??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\pic\artist_trend_0.png
?????文件???????75044??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\pic\artist_trend_predict_0.png
?????文件??????112406??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\pic\song_trend_0.png
?????文件???????22432??2016-06-19?14:09??AliMusicTrendPredict-master\s1d1\pp.py
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\
?????文件???????56254??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_34_play_diffrate.png
?????文件???????80439??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_34_play_pred.png
?????文件???????39008??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_34_play_trend.png
?????文件???????73673??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_99_play.png
?????文件???????90596??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_99_play_month_seasonal.png
?????文件???????54569??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_99_play_trend.png
?????文件??????104886??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\artist_99_play_week_seasonal.png
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\data\
?????文件???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\data\.placeholder
?????文件???????65163??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\iterate.dat
?????文件???????22349??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\le2.py
?????目錄???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\pic_trend\
?????文件???????????0??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\pic_trend\.placeholder
?????文件???????63669??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\pic_trend\0.png
?????文件???????43664??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\pic_trend\1.png
?????文件???????88492??2016-06-19?14:09??AliMusicTrendPredict-master\s1d2\pic_trend\10.png
............此處省略201個文件信息
- 上一篇：西安交通大學計算機網絡原理課件
- 下一篇：spring4源碼
評論
共有 條評論
川公網安備 51152502000135號