मॉडल को फिट करें और मूल्यांकन करें

Keras के साथ Advanced Deep Learning

Zach Deane-Mayer

Data Scientist

बास्केटबॉल डेटा

लक्ष्य: टूर्नामेंट के नतीजे भविष्यवाणी करें

उपलब्ध डेटा: आयोजकों द्वारा दिए गए टीम रेटिंग्स

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

बास्केटबॉल डेटा

इनपुट: Seed difference

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

บาส्केटबॉल डेटा

आउटपुट: Score difference

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

बास्केटबॉल डेटा

इनपुट:

Seed difference - एक संख्या: -15 से +15
Seed रेंज 1-16
अधिकतम अंतर 16-1 = +15
न्यूनतम अंतर 1-16 = -15

आउटपुट:

Score difference - एक संख्या: -50 से +50

बास्केटबॉल डेटा

Seed difference: 15
- Team 1: 16
- Team 2: 1
Seed difference: -15
- Team 1: 1
- Team 2: 16

बास्केटबॉल डेटा

Score difference: -9
- Team 1: 41
- Team 2: 50
Score difference: 6
- Team 1: 61
- Team 2: 55

बास्केटबॉल डेटा

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

मॉडल बनाएँ

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')

मॉडल फिट करें

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)

मॉडल का मूल्यांकन करें

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

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

अभ्यास करते हैं!

Keras के साथ Advanced Deep Learning