Python IndexError: index 1 outside of LDA

Question

I have a dataset that looks like this:

    Out  Revolver   Ratio     Num ...
0   1    0.766127   0.802982  0   ...
1   0    0.957151   0.121876  1 
2   0    0.658180   0.085113  0 
3   0    0.233810   0.036050  3 
4   1    0.907239   0.024926  5 
...

Outcan only take values ​​0 and 1. Then I tried to create PCA and LCA plots using the following code: http://scikit-learn.org/stable/auto_examples/decomposition/plot_pca_vs_lda.html

features = Train.columns[1:]
Xf = newTrain[features]
yf = newTrain.Out
pca = PCA(n_components=2)
X_r = pca.fit(Xf).transform(Xf)
lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(Xf, yf).transform(Xf)

plt.figure()
for c, i, name in zip("rgb", [0, 1], names):
    plt.scatter(X_r[yf == i, 0], X_r[yf == i, 1], c=c, label=name)
plt.legend()
plt.title('PCA plt')

plt.figure()
for c, i, name in zip("rgb", [0, 1], names):
    plt.scatter(X_r2[yf == i, 0], X_r2[yf == i, 1], c=c, label=name)
plt.legend()
plt.title('LDA plt')

I can make the PCA schedule work. However, this does not make sense, since it shows only 2 points. One in the area (-4000, 30), and the other (2400, 23.7). I do not see a lot of data, as in the plot in this link

LDA job does not work and gives an error

IndexError: index 1 is out of bounds for axis 1 with size 1

I also tried the code below to create an LDA chart, but got the same error

for c, i, name in zip("rgb", [0, 1], names):
    plt.scatter(x=X_LDA_sklearn[:, 0][yf==i], y=X_LDA_sklearn[:, 1][yf==i], c=c, label=name)
plt.legend()

Does anyone know what's wrong with that?

EDIT: Here is my import

import pandas as pd
from pandas import Series,DataFrame
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import csv

from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split
from sklearn import metrics
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.lda import LDA

Like where errors occur:

I get

FutureWarning: in the future, boolean array-likes will be handled as a boolean array index
plt.scatter(X_r[yf == i,0], X_r[yf == i, 1], c=c, label=name)

for PCA

LDA

plt.scatter(X_r2[yf == i, 0], X_r2[yf == i, 1], c=c, label=name)

FutureWarning: in the future, boolean array-likes will be handled as a boolean array index

IndexError: index 1 is out of bounds for axis 1 with size 1

Answer 1

, , , X_r2 ( , ). y=X_LDA_sklearn[:, 1][yf==i] , , , , .

( ), . ( - ):

:

import pandas as pd
from pandas import Series,DataFrame
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import csv

from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import train_test_split
from sklearn import metrics
from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

trainDF = pd.DataFrame({'Out': [1, 0, 0, 0, 1, 3, 3],
                        'Revolver': [0.766, 0.957, 0.658, 0.233, 0.907, 0.1, 0.15],
                        'Ratio': [0.803, 0.121, 0.085, 0.036, 0.024, 0.6, 0.8],
                        'Num': [0, 1, 0, 3, 5, 4, 4]})
#drop NA values
trainDF = trainDF.dropna()

trainDF['Num'].loc[(trainDF['Num']==8) | (trainDF['Num']==17)] = trainDF['Num'].median()

# convert dataframe to numpy array
y = trainDF['Out'].as_matrix()

# convert dataframe to numpy array
X = trainDF.drop('Out', 1).as_matrix()

target_names = ['out', 'in']

pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)

lda = LinearDiscriminantAnalysis(n_components=2)
X_r2 = lda.fit(X, y).transform(X)

# Percentage of variance explained for each components
print('explained variance ratio (first two components): %s'
      % str(pca.explained_variance_ratio_))

plt.figure()
for c, i, target_name in zip("rgb", [0, 1], target_names):
    plt.scatter(X_r[y == i, 0], X_r[y == i, 1], c=c, label=target_name)
plt.legend()
plt.title('PCA of Out')

plt.figure()
for c, i, target_name in zip("rgb", [0, 1], target_names):
    plt.scatter(X_r2[y == i, 0], X_r2[y == i, 1], c=c, label=target_name)
plt.legend()
plt.title('LDA of Out')

plt.show()

, "Index out of Bounds", .