python库分析科比生涯数据

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import KFold

filename= "data.csv"
raw = pd.read_csv(filename)
print (raw.shape)
raw.head()

kobe =  raw[pd.notnull(raw['shot_made_flag'])]
print (kobe.shape)

(25697, 25)

alpha = 0.02

plt.figure(figsize=(10,10))

plt.subplot(121)
plt.scatter(kobe.loc_x, kobe.loc_y, color='R', alpha=alpha)
plt.title('loc_x and loc_y')

plt.subplot(122)
plt.scatter(kobe.lon, kobe.lat, color='B', alpha=alpha)
plt.title('lat and lon')

raw['dist'] = np.sqrt(raw['loc_x']**2 + raw['loc_y']**2)

loc_x_zero = raw['loc_x'] == 0

raw['angle'] = np.array([0]*len(raw))
raw['angle'][~loc_x_zero] = np.arctan(raw['loc_y'][~loc_x_zero] / raw['loc_x'][~loc_x_zero])
raw['angle'][loc_x_zero] = np.pi / 2

raw['remaining_time'] = raw['minutes_remaining'] * 60 + raw['seconds_remaining']

print(kobe.action_type.unique())
print(kobe.combined_shot_type.unique())
print(kobe.shot_type.unique())
print(kobe.shot_type.value_counts())

kobe['season'].unique()

array(['2000-01', '2001-02', '2002-03', '2003-04', '2004-05', '2005-06',
'2006-07', '2007-08', '2008-09', '2009-10', '2010-11', '2011-12',
'2012-13', '2013-14', '2014-15', '2015-16', '1996-97', '1997-98',
'1998-99', '1999-00'], dtype=object)

raw['season'] = raw['season'].apply(lambda x: int(x.split('-')[1]) )
raw['season'].unique()

array([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 97,
98, 99, 0], dtype=int64)

print(kobe['team_id'].unique())
print(kobe['team_name'].unique())

[1610612747]
['Los Angeles Lakers']

pd.DataFrame({'matchup':kobe.matchup, 'opponent':kobe.opponent})

plt.figure(figsize=(5,5))

plt.scatter(raw.dist, raw.shot_distance, color='blue')
plt.title('dist and shot_distance')

gs = kobe.groupby('shot_zone_area')
print (kobe['shot_zone_area'].value_counts())
print (len(gs))

Center© 11289
Right Side Center(RC) 3981
Right Side® 3859
Left Side Center(LC) 3364
Left Side(L) 3132
Back Court(BC) 72
Name: shot_zone_area, dtype: int64
6

import matplotlib.cm as cm
plt.figure(figsize=(20,10))

def scatter_plot_by_category(feat):
    alpha = 0.1
    gs = kobe.groupby(feat)
    cs = cm.rainbow(np.linspace(0, 1, len(gs)))
    for g, c in zip(gs, cs):
        plt.scatter(g[1].loc_x, g[1].loc_y, color=c, alpha=alpha)

plt.subplot(131)
scatter_plot_by_category('shot_zone_area')
plt.title('shot_zone_area')

plt.subplot(132)
scatter_plot_by_category('shot_zone_basic')
plt.title('shot_zone_basic')

plt.subplot(133)
scatter_plot_by_category('shot_zone_range')
plt.title('shot_zone_range')

drops = ['shot_id', 'team_id', 'team_name', 'shot_zone_area', 'shot_zone_range', 'shot_zone_basic', \
         'matchup', 'lon', 'lat', 'seconds_remaining', 'minutes_remaining', \
         'shot_distance', 'loc_x', 'loc_y', 'game_event_id', 'game_id', 'game_date']
for drop in drops:
    raw = raw.drop(drop, 1)

print (raw['combined_shot_type'].value_counts())
pd.get_dummies(raw['combined_shot_type'], prefix='combined_shot_type')[0:2]

categorical_vars = ['action_type', 'combined_shot_type', 'shot_type', 'opponent', 'period', 'season']
for var in categorical_vars:
    raw = pd.concat([raw, pd.get_dummies(raw[var], prefix=var)], 1)
    raw = raw.drop(var, 1)

train_kobe = raw[pd.notnull(raw['shot_made_flag'])]

train_label = train_kobe['shot_made_flag']
train_kobe = train_kobe.drop('shot_made_flag', 1)

test_kobe = raw[pd.isnull(raw['shot_made_flag'])]
test_kobe = test_kobe.drop('shot_made_flag', 1)

from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import confusion_matrix,log_loss
import time

import numpy as np
range_m = np.logspace(0,2,num=5).astype(int)
range_m

array([ 1, 3, 10, 31, 100])

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import KFold

print('Finding best n_estimators for RandomForestClassifier...')
min_score = 100000
best_n = 0
scores_n = []
range_n = np.logspace(0,2,num=3).astype(int)
for n in range_n:
    print("the number of trees : {0}".format(n))
    t1 = time.time()

    rfc_score = 0.

    rfc = RandomForestClassifier(n_estimators=n)
    for train_k, test_k in KFold(10, shuffle=True).split(train_kobe):
        rfc.fit(train_kobe.iloc[train_k], train_label.iloc[train_k])

        pred = rfc.predict(train_kobe.iloc[test_k])
        rfc_score += log_loss(train_label.iloc[test_k], pred) / 10
    scores_n.append(rfc_score)
    if rfc_score < min_score:
        min_score = rfc_score
        best_n = n

    t2 = time.time()
    print('Done processing {0} trees ({1:.3f}sec)'.format(n, t2-t1))
print(best_n, min_score)

print('Finding best max_depth for RandomForestClassifier...')
min_score = 100000
best_m = 0
scores_m = []
range_m = np.logspace(0,2,num=3).astype(int)
for m in range_m:
    print("the max depth : {0}".format(m))
    t1 = time.time()

    rfc_score = 0.

    rfc = RandomForestClassifier(max_depth=m, n_estimators=best_n)
    for train_k, test_k in KFold(10, shuffle=True).split(train_kobe):
        rfc.fit(train_kobe.iloc[train_k], train_label.iloc[train_k])

        pred = rfc.predict(train_kobe.iloc[test_k])
        rfc_score += log_loss(train_label.iloc[test_k], pred) / 10
    scores_m.append(rfc_score)
    if rfc_score < min_score:
        min_score = rfc_score
        best_m = m

    t2 = time.time()
    print('Done processing {0} trees ({1:.3f}sec)'.format(m, t2-t1))
print(best_m, min_score)

Finding best n_estimators for RandomForestClassifier...

the number of trees : 1
Done processing 1 trees (0.973sec)
the number of trees : 10
Done processing 10 trees (5.755sec)
the number of trees : 100
Done processing 100 trees (51.947sec)
100 11.914000011353393
Finding best max_depth for RandomForestClassifier...

the max depth : 1
Done processing 1 trees (4.065sec)
the max depth : 10
Done processing 10 trees (16.296sec)
the max depth : 100
Done processing 100 trees (49.635sec)
10 11.040351953558947

plt.figure(figsize=(10,5))
plt.subplot(121)
plt.plot(range_n, scores_n)
plt.ylabel('score')
plt.xlabel('number of trees')

plt.subplot(122)
plt.plot(range_m, scores_m)
plt.ylabel('score')
plt.xlabel('max depth')

model = RandomForestClassifier(n_estimators=best_n, max_depth=best_m)
model.fit(train_kobe, train_label)

报错问题解决

for train_k, test_k in KFold(len(train_kobe), n_folds=10, shuffle=True):会报很多错
需要改为for train_k, test_k in KFold(10, shuffle=True).split(train_kobe):

Original: https://blog.csdn.net/qq_43966129/article/details/122799128
Author: 最白の白菜
Title: 实战项目-python库分析科比生涯数据

相关阅读

Title: Ubuntu anaconda换源(最新最全亲测)

文章目录

• 前言
• 一、anaconda换源(适用linux和window)
  *
  -
  +
  • 方法一：命令行换源
  • 方法二：可视化界面换源（推荐新手）
• 二、anaconda删除源
  *
  -
  +
  • 方法一：命令行删除
  • 方法二：可视化界面删除（推荐新手）
• 三、anaconda还原默认源
• 总结

前言

其他的热门教程时间跳过久远，部分链接已经失效。
下面就是换源的全部流程。本文写于 2021.07.15保证时效性，亲测可用。

提示：以下是本篇文章正文内容，下面案例可供参考

一、anaconda换源(适用linux和window)

换源的原因：anacond默认的源下载python包太慢，时间太长。所以需要更换国内的源。

终端输入以下命令回车：注：以添加清华源为例

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/msys2
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/bioconda
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/menpo
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/simpleitk

检查是否换源成功！！！终端输入以下命令：

conda config --set show_channel_urls yes
conda info

注：可以看到此时 channel URLs 已经全部更换为清华源。

如果需要更换中科大源可使用以下命令：

conda config --add channels https://mirrors.ustc.edu.cn/anaconda/pkgs/main/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/conda-forge/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/msys2/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/bioconda/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/menpo/
conda config --add channels https://mirrors.ustc.edu.cn/anaconda/cloud/pytorch/

检查步骤同上

最后 建议删除defaut的默认源(推荐) 删除方法见下方。[不删除的话，下载python包的速度有可能仍然会很慢]

注：使用conda info 可以看到anaconda的默认源 仍然存在，但是排放在下面。

终端输入 anaconda-navigator启动可视化界面 轻松完成channel源的添加，删除，检查。 在换国内源的时候，将网址一条条输入 后 update即可。

; 二、anaconda删除源

在终端输入如下命令：注意：以删除清华源为例，在命令后面加上相应的URL。逐一删除

conda config --remove channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/

这个很简单，没啥好说的。上面有提及，删除对应网址即可。

三、anaconda还原默认源

注：常用语重置下载源，省去逐个删除URLs的时间
终端输入以下命令： conda config --remove-key channels

总结

提示：以上就是换源的全部流程。本文写于 2021.07.15保证时效性，亲测可用。

anaconda常用命令
anaconda配置Pytorch环境
anaconda配置Tensorflow环境

如果这个图文教程有帮助到你的话，能点个免费的赞吗n(≧▽≦)n。其他问题也请留言在评论区哦，博主看到会回复的。O(∩_∩)O~

如果想要安装配置特殊环境如pytorch或者TensorFlow等或者可以学习anaconda的使用，后续可以查阅博主的其他博客。

Original: https://blog.csdn.net/KIK9973/article/details/118776314
Author: 向日葵骑士Faraday
Title: Ubuntu anaconda换源(最新最全亲测)