拟合并评估模型

使用 Keras 的高级深度学习

Zach Deane-Mayer

Data Scientist

篮球数据

目标：预测锦标赛结果

可用数据：主办方提供的球队种子评级

import pandas as pd
games_tourney = pd.read_csv('datasets/games_tourney.csv')
games_tourney.head()

Out[1]:
   season  team_1  team_2  home  seed_diff  score_diff  score_1  score_2  won
0    1985     288      73     0         -3          -9       41       50    0
1    1985    5929      73     0          4           6       61       55    1
2    1985    9884      73     0          5          -4       59       63    0
3    1985      73     288     0          3           9       50       41    1
4    1985    3920     410     0          1          -9       54       63    0

篮球数据

输入：种子差

import pandas as pd
games_tourney = pd.read_csv('datasets/games_tourney.csv')
games_tourney.head()

篮球数据

输出：分差

import pandas as pd
games_tourney = pd.read_csv('datasets/games_tourney.csv')
games_tourney.head()

篮球数据

输入：

种子差：单一数值，-15 至 +15
种子范围 1–16
最大差：16-1 = +15
最小差：1-16 = -15

输出：

分差：单一数值，-50 至 +50

篮球数据

种子差：15
- 队1：16
- 队2：1
种子差：-15
- 队1：1
- 队2：16

篮球数据

分差：-9
- 队1：41
- 队2：50
分差：6
- 队1：61
- 队2：55

篮球数据

import pandas as pd
games_tourney = pd.read_csv('datasets/games_tourney_samp.csv')
games_tourney.head()

Out[1]:
   season  team_1  team_2  home  seed_diff  score_diff  score_1  score_2  won
0    2017     320    6323     0         13          18      100       82    1
1    2017    6323     320     0        -13         -18       82      100    0

构建模型

from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Dense
input_tensor = Input(shape=(1,))
output_tensor = Dense(1)(input_tensor)
model = Model(input_tensor, output_tensor)
model.compile(optimizer='adam', loss='mae')

训练模型

from pandas import read_csv
games = read_csv('datasets/games_tourney.csv')
model.fit(games['seed_diff'],
          games['score_diff'],
          batch_size=64,
          validation_split=.20,
          verbose=True)

评估模型

model.evaluate(games_test['seed_diff'],
               games_test['score_diff'])

1000/1000 [==============================] - 0s 26us/step
Out[1]: 9.145421981811523

Passons à la pratique !

使用 Keras 的高级深度学习