Träna och utvärdera en modell

Avancerad djupinlärning med Keras

Zach Deane-Mayer

Data Scientist

Basketballdata

Mål: Förutsäg turnéringsresultat

Tillgänglig data: lagbetyg från turnéringsorganisatörerna

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

Basketballdata

Indata: Seedningsdifferens

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

Basketballdata

Utdata: Poängdifferens

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

Basketballdata

Indata:

Seedningsdifferens – ett tal: -15 till +15
Seedning varierar från 1–16
Högsta differens: 16-1 = +15
Lägsta differens: 1-16 = -15

Utdata:

Poängdifferens – ett tal: -50 till +50

Basketballdata

Seedningsdifferens: 15
- Lag 1: 16
- Lag 2: 1
Seedningsdifferens: -15
- Lag 1: 1
- Lag 2: 16

Basketballdata

Poängdifferens: -9
- Lag 1: 41
- Lag 2: 50
Poängdifferens: 6
- Lag 1: 61
- Lag 2: 55

Basketballdata

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

Bygg modellen

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')

Träna modellen

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)

Utvärdera modellen

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

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

Nu kör vi en övning!

Avancerad djupinlärning med Keras