[KNN- NBA球员

Question

我正在与Dataquest上的Python教程中的K近邻一起工作。几个月来一直在处理这些问题，每次都是新问题。我只剩下最后几行代码，但无法弄清楚为什么每次尝试在训练数据上拟合模型时都会出现以下错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-59-0e474d4c7797> in <module>()
----> 1 knn.fit(train[x_columns], train[y_column])

C:\Users\aduran\AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\neighbors\base.py in fit(self, X, y)
    739         """
    740         if not isinstance(X, (KDTree, BallTree)):
--> 741             X, y = check_X_y(X, y, "csr", multi_output=True)
    742         self._y = y
    743         return self._fit(X)

C:\Users\aduran\AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_X_y(X, y, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, multi_output, ensure_min_samples, ensure_min_features, y_numeric, warn_on_dtype, estimator)
    519     X = check_array(X, accept_sparse, dtype, order, copy, force_all_finite,
    520                     ensure_2d, allow_nd, ensure_min_samples,
--> 521                     ensure_min_features, warn_on_dtype, estimator)
    522     if multi_output:
    523         y = check_array(y, 'csr', force_all_finite=True, ensure_2d=False,

C:\Users\aduran\AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    405                              % (array.ndim, estimator_name))
    406         if force_all_finite:
--> 407             _assert_all_finite(array)
    408 
    409     shape_repr = _shape_repr(array.shape)

C:\Users\aduran\AppData\Local\Continuum\Anaconda3\lib\site-packages\sklearn\utils\validation.py in _assert_all_finite(X)
     56             and not np.isfinite(X).all()):
     57         raise ValueError("Input contains NaN, infinity"
---> 58                          " or a value too large for %r." % X.dtype)
     59 
     60 

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

下面提供了我的代码，并提供了实际study的链接。关于为何执行knn.fit(train[x_columns], train[y_column]代码时出现上述错误消息的任何帮助都将有所帮助。

    import pandas
with open("C:/Users/aduran/Downloads/nba_data.csv", 'r') as csvfile:
    nba = pandas.read_csv(csvfile)

print(nba.columns.values)

#Select Lebron James from our dataset
selected_player = nba[nba["player"] == "LeBron James"].iloc[0]

#Choose only the numeric columns(we'll use for computing euclidean distance)
distance_columns = ['age', 'g', 'gs', 'mp', 'fg', 'fga',
'fg.', 'x3p', 'x3pa', 'x3p.', 'x2p', 'x2pa', 'x2p.', 'efg.', 'ft',
'fta', 'ft.', 'orb', 'drb', 'trb', 'ast', 'stl', 'blk', 'tov', 'pf',
'pts']

#create euclidean distance
def euclidean_distance(row) :
    inner_value = 0

    for k in distance_columns:
        print(k)
        print(selected_player[k])
        inner_value += (row[k] - selected_player[k]) ** 2
        print(inner_value)
        print('-----')
        print(math.sqrt(inner_value))
    print('=====')
    return math.sqrt(inner_value)

import math

#find the distance from each player in the dataset to LeBron
lebron_distance = nba.apply(euclidean_distance, axis = 1)

#Select only the numeric columns from the NBA dataset
nba_numeric = nba[distance_columns]

#NORMALIZE ALL OF THE NUMERIC COLUMNS
nba_normalized = (nba_numeric - nba_numeric.mean() / nba_numeric.std())

#Finding the nearest neighbor
from scipy.spatial import distance

#Fill in the NA values in nba_normalized
nba_normalized.fillna(0, inplace=True)

#Find the normalized vector for Lebron James
lebron_normalized = nba_normalized[nba["player"] == "LeBron James"]

#Find the distance between Lebron James and everyon else
euclidean_distances = nba_normalized.apply(lambda row:
                        distance. euclidean(row, lebron_normalized), axis=1)

# Create a new dataframe with distances.
distance_frame = pandas.DataFrame(data={"dist": euclidean_distances, "idx": euclidean_distances.index})
distance_frame.sort("dist", inplace=True)

#Find the most similiar player to LeBron
second_smallest = distance_frame.iloc[1]["idx"] 
most_similiar_to_lebron = nba.loc[int(second_smallest)]["player"]

#Generating Training and testing sets to accomodate overfitting

import random
from numpy.random import permutation

#Randomly shuffle the index of the nba
random_indices = permutation(nba.index)

#Set cutoff for how many items we want in the test set (in this case 1/3)
test_cutoff = math.floor(len(nba)/3)

#Generate the test set by taking the first 1/3 of the randomly shuffled indices
test = nba.loc[random_indices[1:test_cutoff]]

#Generate the train set with the rest of the data
train = nba.loc[random_indices[test_cutoff:]]

#The columns that weill be making predictions with
x_columns = ['age', 'g', 'gs', 'mp', 'fg', 'fga',
'fg.', 'x3p', 'x3pa', 'x3p.', 'x2p', 'x2pa', 'x2p.', 'efg.', 'ft',
'fta', 'ft.', 'orb', 'drb', 'trb', 'ast', 'stl', 'blk', 'tov', 'pf']

#the column that we want to predict
y_column = ["pts"] 

from sklearn.neighbors import KNeighborsRegressor

#Create the knn model #Look at the 5 closest neighbors
knn = KNeighborsRegressor(n_neighbors=5)

#Fit the model on the training data
knn.fit(train[x_columns], train[y_column])

Answer 1

只需添加此行

nba.fillna(0, inplace=True) 

第三行之后，即print(nba.columns.values)