I have a pandas dataframe for a term x document matrix. I need to extract only those values that appear in a separate list of terms (extracted from a different source).
The list TestDict contains terms. E.g., ['аборенков','абсолютно',...]
-- to create a term by document matrix (reused)
def fn_tdm_df(docs, xColNames = None, **kwargs):
#initialize the vectorizer
vectorizer = CountVectorizer(**kwargs)
x1 = vectorizer.fit_transform(docs)
#create dataFrame
df = pd.DataFrame(x1.toarray().transpose(), index = vectorizer.get_feature_names())
if xColNames is not None:
df.columns = xColNames
return df
Then later in the code I have:
for filename in os.listdir(DIR):
d1 = fn_tdm_df(docs = MyCorpus(DIR)['docs'])
The output of d1.head(5):
0 1 2 3 4 5 6 7 8 9 ... 27 28 29 30 31 \
аборенков 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0
аборенкова 0 0 0 0 0 0 0 0 0 0 ... 0 0 0 0 0
абсолютно 0 0 0 0 0 0 0 0 0 1 ... 0 0 0 0 0
авантюру 0 0 0 0 1 0 0 0 0 0 ... 0 0 0 0 0
аварии 0 0 1 0 0 0 0 0 0 0 ... 0 0 0 0 0
32 33 34 35 36
аборенков 0 0 0 2 0
аборенкова 0 0 0 1 0
абсолютно 0 0 0 0 0
авантюру 0 0 0 0 0
аварии 0 0 0 0 0
I'm doing something like:
with open("TestTD", "w", encoding = "utf-8") as f:
for w in d1.index: # d1 is my dataframe
if w in TestDict:
np.savetxt(f, d1.loc(w),fmt='%d')
But I don't think the .loc(w) is what I want...
Related
I am trying to parse a .log file using python for the Status information about processes of a linux system. The .log file has a lot of different sections of information, the sections of interest start with "##START-ALLPROCESSES-xxxxxxxx" where x is the epoch date and end with '##END-ALLPROCESSES-xxxxxxx". After this line each process is listed with 52 columns each, the number of processes may change depending on the info recorded at the time, and there may be multiple sections with this information at different times.
The idea is to open the .log file, find the sections and then use the XXXXXXX as the key for a nested dictionary where the keys are the predefined column dates filled in with the values from the section, and do this for all different sections that would be found on the .log fie. The nested dictionary would look something like below
[date1-XXXXXX:
[ columnName1: process1,
.
.
.
columnName52: info1
],
.
.
.
[ columnName1: process52,
.
.
.
columName52: info52
]
],
[date2-XXXXXX:
[ columnName1: process1,
.
.
.
columnName52: info1
],
.
.
.
[ columnName1: process52,
.
.
.
columName52: info52
]
]
The data in the .log file looks as follow and would have multiple sections as this but with a different date each line starts with the process id and (process name)
##START-ALLPROCESSES-1676652419
1 (systemd) S 0 1 1 0 -1 4210944 2070278 9743969773 2070 2703 8811 11984 7638026 9190549 20 0 1 0 0 160043008 745 18446744073709551615 187650352414720 187650353516788 281474853505456 0 0 0 671173123 4096 1260 1 0 0 17 0 0 0 2706 0 0 187650353585800 187650353845340 187651263758336 281474853506734 281474853506745 281474853506745 281474853507053 0
10 (rcu_bh) I 2 0 0 0 -1 2129984 0 0 0 0 0 0 0 0 20 0 1 0 2 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0
10251 (kworker/1:2) I 2 0 0 0 -1 69238880 0 0 0 0 0 914 0 0 20 0 1 0 617684776 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 1 0 0 0 0 0 0 0 0 0 0 0 0 0
10299 (loop2) S 2 0 0 0 -1 3178560 0 0 0 0 0 24 0 0 0 -20 1 0 10871 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 0 0 169 0 0 0 0 0 0 0 0 0 0
10648 (kworker/2:0) I 2 0 0 0 -1 69238880 0 0 0 0 0 567 0 0 20 0 1 0 663634994 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 2 0 0 0 0 0 0 0 0 0 0 0 0 0
1082 (nvme-wq) I 2 0 0 0 -1 69238880 0 0 0 0 0 0 0 0 0 -20 1 0 109 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 3 0 0 0 0 0 0 0 0 0 0 0 0 0
1095 (scsi_eh_0) S 2 0 0 0 -1 2129984 0 0 0 0 0 0 0 0 20 0 1 0 110 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 3 0 0 0 0 0 0 0 0 0 0 0 0 0
1096 (scsi_tmf_0) I 2 0 0 0 -1 69238880 0 0 0 0 0 0 0 0 0 -20 1 0 110 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1099 (scsi_eh_1) S 2 0 0 0 -1 2129984 0 0 0 0 0 0 0 0 20 0 1 0 110 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0
11 (migration/0) S 2 0 0 0 -1 69238848 0 0 0 0 0 4961 0 0 -100 0 1 0 2 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 99 1 0 0 0 0 0 0 0 0 0 0 0
1100 (scsi_tmf_1) I 2 0 0 0 -1 69238880 0 0 0 0 0 0 0 0 0 -20 1 0 110 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483647 0 1 0 0 17 0 0 0 0 0 0 0 0 0 0 0 0 0 0
##END-ALLPROCESSES-1676652419
I have tried it multiple ways but I cannot seem to get it to go correctly, my last attempt
columns = ['pid', 'comm', 'state', 'ppid', 'pgrp', 'session', 'tty_nr', 'tpgid', 'flags', 'minflt', 'cminflt', 'majflt', 'cmajflt', 'utime', 'stime',
'cutime', 'cstime', 'priority', 'nice', 'num_threads', 'itrealvalue', 'starttime', 'vsize', 'rss', 'rsslim', 'startcode', 'endcode', 'startstack', 'kstkesp',
'kstkeip', 'signal', 'blocked', 'sigignore', 'sigcatch', 'wchan', 'nswap', 'cnswap', 'exit_signal', 'processor', 'rt_priority', 'policy', 'delayacct_blkio_ticks',
'guest_time', 'cguest_time', 'start_data', 'end_data', 'start_brk', 'arg_start', 'arg_end', 'env_start', 'env_end', 'exit_code' ]
for file in os.listdir(dir):
if file.endswith('.log'):
with open(file, 'r') as f:
data = f.read()
data = data.split('##START-ALLPROCESSES-')
data = data[1:]
for i in range(len(data)):
data[i] = data[i].split('##END-ALLPROCESSES-')
data[i] = data[i][0]
data[i] = re.split('\r', data[i])
data[i] = data[i][0]
data[i] = re.split('\n', data[i])
for j in range(len(data[i])):
data[i][j] = re.split('\s+', data[i][j])
#print(data[i])
data[i][0] = str(data[i][0])
data_dict = {}
for i in range(len(data)):
data_dict[data[i][0]] = {}
for j in range(len(columns)):
data_dict[data[i][0]][columns[j]] = data[i][j+1]
print(data_dict)
I converted the epoch date into a str as I was getting unhashable list errors, however that made it so the epoch date shows as a key but each column now has the entire list for the 52 columms of information as a single one, so definitely I am missing something
To solve this problem, you could follow the following steps:
Open the .log file and read the contents
Search for all the sections of interest by finding lines that start with "##START-ALLPROCESSES-" and end with "##END-ALLPROCESSES-"
For each section found, extract the epoch date and create a dictionary with an empty list for each of the 52 columns
Iterate over the lines within the section and split the line into the 52 columns using space as a separator. Add the values to the corresponding list in the dictionary created in step 3
Repeat steps 3 and 4 for all the sections found in the .log file
Return the final nested dictionary
Here is some sample code that implements these steps:
import re
def parse_log_file(log_file_path):
with open(log_file_path, 'r') as log_file:
log_contents = log_file.read()
sections = re.findall(r'##START-ALLPROCESSES-(.*?)##END-ALLPROCESSES-', log_contents, re.DOTALL)
nested_dict = {}
for section in sections:
lines = section.strip().split('\n')
epoch_date = lines[0].split('-')[-1]
column_names = ['column{}'.format(i) for i in range(1, 53)]
section_dict = {column_name: [] for column_name in column_names}
for line in lines[1:]:
values = line.strip().split()
for i, value in enumerate(values):
section_dict[column_names[i]].append(value)
nested_dict['date{}-{}'.format(epoch_date, len(section_dict['column1']))] = section_dict
return nested_dict
You can call this function by passing the path to the .log file as an argument. The function returns the nested dictionary described in the problem statement.
I am trying to add and element at a specific index.
My output:
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
I am expecting an output that prints a '/' at an index position of matrix[5][5] like below-
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 / 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
The code I wrote is-
R = 10 #int(input("Enter the number of rows:"))
C = 10 #int(input("Enter the number of columns:"))
# Initialize matrix
matrix = []
print("Enter the entries rowwise:")
# For user input
for i in range(R): # A for loop for row entries
a =[]
for j in range(C): # A for loop for column entries
a.append(0)
matrix.append(a)
#print("/",matrix[index[20]][index[10]])
#matrix.insert([0][0],'/')
for i in range(R):
for j in range(C):
print(matrix[i][j], end = " ")
print()
I tried-
matrix.insert([0][0],'/')
But this caused an error as-
shubham#IAMSB:~$ python3 final.py
Enter the entries rowwise:
/ Traceback (most recent call last):
File "final.py", line 18, in <module>
print(matrix[i][j], end = " ")
IndexError: string index out of range
Please forgive my mistakes I new to PYTHON
Thanks in Advance!
Simplest is you can have an if condition when you are populating the list.
In [156]: R = 10 #int(input("Enter the number of rows:"))
...: C = 10 #int(input("Enter the number of columns:"))
...: # Initialize matrix
...: matrix = []
...: print("Enter the entries rowwise:")
...:
...: # For user input
...: for i in range(R): # A for loop for row entries
...: a =[]
...: for j in range(C): # A for loop for column entries
...: a.append(0)
...: if i == 4 and j == 3:
...: a.append("/")
...: matrix.append(a)
...: #print("/",matrix[index[20]][index[10]])
...: #matrix.insert([0][0],'/')
...: for i in range(R):
...: for j in range(C):
...: print(matrix[i][j], end = " ")
...: print()
...:
Enter the entries rowwise:
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 / 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
Update:
In [180]: R = 10 #int(input("Enter the number of rows:"))
...: C = 10 #int(input("Enter the number of columns:"))
...: # Initialize matrix
...: matrix = []
...: print("Enter the entries rowwise:")
...:
...: # For user input
...: for i in range(R): # A for loop for row entries
...: a =[]
...: for j in range(C): # A for loop for column entries
...: a.append(0)
...: matrix.append(a)
...: matrix[(R//2)-1].insert((C//2)-1, "/")
...: #print("/",matrix[index[20]][index[10]])
...: #matrix.insert([0][0],'/')
...: for i in range(R):
...: for j in range(C):
...: print(matrix[i][j], end = " ")
...: print()
...:
Enter the entries rowwise:
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 / 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0
Not going to lie I copied and modified code from this source here:https://www.geeksforgeeks.org/python-using-2d-arrays-lists-the-right-way/
It explains how to use it and why it works.
rows = int(input("Enter row size: "))
cols = int(input("Enter col size: "))
rowPlacement = int(input("What row to place maker: "))
colPlacement = int(input("What col to place maker: "))
arr = [["X" for i in range(cols + 1)] for j in range(rows + 1)]
arr[rowPlacement][colPlacement] = str("O")
for row in arr:
print(row)
I have a dataframe which looks like this:
I1 I2 V
0 1 1 300
1 1 5 7
2 1 9 3
3 2 2 280
4 2 3 4
5 5 1 5
6 5 5 400
I1 and I2 represent indexes while V represent values.
The indexes with values equal to 0 have been omitted, but I'd like to get a confusion matrix showing all the values, i.e. something like this:
1 2 3 4 5 6 7 8 9
1 300 0 0 0 7 0 0 0 3
2 0 280 4 0 0 0 0 0 0
3 0 0 0 0 0 0 0 0 0
4 0 0 0 0 0 0 0 0 0
5 5 0 0 0 400 0 0 0 0
6 0 0 0 0 0 0 0 0 0
7 0 0 0 0 0 0 0 0 0
8 0 0 0 0 0 0 0 0 0
9 0 0 0 0 0 0 0 0 0
How can I do it?
Thanks in advance!
Use set_index with unstack for reshape, for append missing values add reindex and for data cleaning rename_axis :
r = range(1, 10)
df = (df.set_index(['I1','I2'])['V']
.unstack(fill_value=0)
.reindex(index=r, columns=r, fill_value=0)
.rename_axis(None)
.rename_axis(None, axis=1))
print (df)
1 2 3 4 5 6 7 8 9
1 300 0 0 0 7 0 0 0 3
2 0 280 4 0 0 0 0 0 0
3 0 0 0 0 0 0 0 0 0
4 0 0 0 0 0 0 0 0 0
5 5 0 0 0 400 0 0 0 0
6 0 0 0 0 0 0 0 0 0
7 0 0 0 0 0 0 0 0 0
8 0 0 0 0 0 0 0 0 0
9 0 0 0 0 0 0 0 0 0
Detail:
print (df.set_index(['I1','I2'])['V']
.unstack(fill_value=0))
I2 1 2 3 5 9
I1
1 300 0 0 7 3
2 0 280 4 0 0
5 5 0 0 400 0
Alternative solution with pivot, if all values are integers:
r = range(1, 10)
df = (df.pivot('I1','I2', 'V')
.fillna(0)
.astype(int)
.reindex(index=r, columns=r, fill_value=0)
.rename_axis(None)
.rename_axis(None, axis=1))
print (df)
1 2 3 4 5 6 7 8 9
1 300 0 0 0 7 0 0 0 3
2 0 280 4 0 0 0 0 0 0
3 0 0 0 0 0 0 0 0 0
4 0 0 0 0 0 0 0 0 0
5 5 0 0 0 400 0 0 0 0
6 0 0 0 0 0 0 0 0 0
7 0 0 0 0 0 0 0 0 0
8 0 0 0 0 0 0 0 0 0
9 0 0 0 0 0 0 0 0 0
Option 1: Using numpy you can
In [150]: size = df[['I1', 'I2']].values.max()
In [151]: arr = np.zeros((size, size))
In [152]: arr[df.I1-1, df.I2-1] = df.V
In [153]: idx = np.arange(1, size+1)
In [154]: pd.DataFrame(arr, index=idx, columns=idx).astype(int)
Out[154]:
1 2 3 4 5 6 7 8 9
1 300 0 0 0 7 0 0 0 3
2 0 280 4 0 0 0 0 0 0
3 0 0 0 0 0 0 0 0 0
4 0 0 0 0 0 0 0 0 0
5 5 0 0 0 400 0 0 0 0
6 0 0 0 0 0 0 0 0 0
7 0 0 0 0 0 0 0 0 0
8 0 0 0 0 0 0 0 0 0
9 0 0 0 0 0 0 0 0 0
Option 2: Using scipy.sparse.csr_matrix
In [178]: from scipy.sparse import csr_matrix
In [179]: size = df[['I1', 'I2']].values.max()
In [180]: idx = np.arange(1, size+1)
In [181]: pd.DataFrame(csr_matrix((df['V'], (df['I1']-1, df['I2']-1)), shape=(size, si
...: ze)).toarray(), index=idx, columns=idx)
Out[181]:
1 2 3 4 5 6 7 8 9
1 300 0 0 0 7 0 0 0 3
2 0 280 4 0 0 0 0 0 0
3 0 0 0 0 0 0 0 0 0
4 0 0 0 0 0 0 0 0 0
5 5 0 0 0 400 0 0 0 0
6 0 0 0 0 0 0 0 0 0
7 0 0 0 0 0 0 0 0 0
8 0 0 0 0 0 0 0 0 0
9 0 0 0 0 0 0 0 0 0
I'm trying to set up a linear regression model in order to predict traffic counts based on the day, and the time of day. Since both are categorical variables, I have to create dummy variables. The get_dummies function makes this very easy, when doing this for both variables individually. However, in the case of predicting traffic volumes, the interdependence between the day and the time of day are important. Therefore, I'll need dummies for all days * all time intervals.
I made a small example, avoiding to trouble you with big datasets:
import pandas as pd
df = pd.DataFrame({'Day': ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'],
'Time': [11,15,9,15,17,10,20],
'Count': [100,150,150,150,180,60,50]})
df_dummies = pd.get_dummies(df.Day)
print(df_dummies)
Results in a nice dataframe with dummies:
Fri Mon Sat Sun Thu Tue Wed
0 0 1 0 0 0 0 0
1 0 0 0 0 0 1 0
2 0 0 0 0 0 0 1
3 0 0 0 0 1 0 0
4 1 0 0 0 0 0 0
5 0 0 1 0 0 0 0
6 0 0 0 1 0 0 0
So what I'm after is something like this:
import pandas as pd
df = pd.DataFrame({'Day': ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'],
'Time': [11,15,9,15,17,10,20],
'Count': [100,150,150,150,180,60,50]})
df_dummies = pd.get_dummies(df.Day * df.Time)
print(df_dummies)
With a result like this:
Fri_9 Fri_15 Mon_9 Mon_15 Sat_9 Sat_15 Sun_9 ...
0 0 1 0 0 0 0 0 ...
1 0 0 0 0 0 1 0 ...
2 0 0 0 0 0 0 1 ...
3 0 0 0 0 1 0 0 ...
4 1 0 0 0 0 0 0 ...
5 0 0 1 0 0 0 0 ...
6 0 0 0 1 0 0 0 ...
7 0 0 0 0 0 0 0 ...
[...]
Is there any way in which this can be done elegantly?
I belive need join columns together with cast to strings:
df_dummies = pd.get_dummies(df.Day + '_' + df.Time.astype(str))
#df_dummies = pd.get_dummies(df.Day.str.cat(df.Time.astype(str), sep='_'))
print(df_dummies)
Fri_17 Mon_11 Sat_10 Sun_20 Thu_15 Tue_15 Wed_9
0 0 1 0 0 0 0 0
1 0 0 0 0 0 1 0
2 0 0 0 0 0 0 1
3 0 0 0 0 1 0 0
4 1 0 0 0 0 0 0
5 0 0 1 0 0 0 0
6 0 0 0 1 0 0 0
I'm trying to set up a linear regression model in order to predict
Technically, you can make a dummy of the tuples:
>>> pd.get_dummies(df[['Day', 'Time']].apply(tuple, axis=1))
(Fri, 17) (Mon, 11) (Sat, 10) (Sun, 20) (Thu, 15) (Tue, 15) (Wed, 9)
0 0 1 0 0 0 0 0
1 0 0 0 0 0 1 0
2 0 0 0 0 0 0 1
3 0 0 0 0 1 0 0
4 1 0 0 0 0 0 0
5 0 0 1 0 0 0 0
6 0 0 0 1 0 0 0
...
however, I think this approach is not the best at the ML level. This will probably fragment the data very much, making things hard for your regressor. You might consider using a gradient-boosted decision tree, if you're after the interactions.
I am dealing a rare error while making some machine learning with a dataset loaded using pandas.
This is the error I am getting:
I have been reading something releated to it and it seems to be due to the columns and how pandas interpret them but I have no clue what can be wrong.
This is the code I am using for this:
import pandas as pd
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/pima-
indians-diabetes/pima-indians-diabetes.data'
col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi',
'pedigree', 'age', 'label']
pima = pd.read_csv(url, header=None, names=col_names)
# define X and y
feature_cols = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi',
'pedigree', 'age']
X = pima[feature_cols]
y = pima.label
#k fold cv
from sklearn.model_selection import KFold, cross_val_score
kf = KFold(n_splits=10) #define number of splits
kf.get_n_splits(X) #to check how many splits will be done.
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
clf = LinearDiscriminantAnalysis() #select the model for train, test in kf.split(X, y):
for train, test in kf.split(X, y):
y_pred_prob = clf.fit(X[train], y[train]).predict_proba(X[test])
y_pred_class = clf.predict(X[test])
Thanks in advance
In clf.fit method, according to the document parameters expected are array:
Parameters
----------
X : array-like, shape (n_samples, n_features)
Training data.
y : array, shape (n_samples,)
If you look at the example in link X and y are numpy array:
Try using as_matrix() for both X and y instead of just X = pima[feature_cols] and y = pima.label
X = pima[feature_cols].as_matrix()
y = pima.label.as_matrix()
Testing by print:
import pandas as pd
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/pima-indians-diabetes/pima-indians-diabetes.data'
col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age', 'label']
pima = pd.read_csv(url, header=None, names=col_names)
# define X and y
feature_cols = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age']
X = pima[feature_cols].as_matrix()
y = pima.label.as_matrix()
#k fold cv
from sklearn.model_selection import KFold, cross_val_score
kf = KFold(n_splits=10) #define number of splits
kf.get_n_splits(X) #to check how many splits will be done.
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
clf = LinearDiscriminantAnalysis() #select the model for train, test in kf.split(X, y):
for train, test in kf.split(X, y):
y_pred_prob = clf.fit(X[train], y[train]).predict_proba(X[test])
y_pred_class = clf.predict(X[test])
print(y_pred_class)
Result:
[1 0 1 0 1 0 0 1 1 0 0 1 1 1 1 0 0 0 0 0 0 0 1 0 1 0 1 0 1 0 0 1 0 0 0 0 1
0 0 1 1 1 0 1 1 1 0 0 0 0 0 0 0 1 1 0 1 0 1 0 0 1 0 0 0 0 0 0 0 0 0 0 1 0
0 0 0]
[0 1 0 0 0 0 0 1 0 1 0 1 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 1 1 0 0
1 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
0 1 1]
[1 1 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 1 1 1 0 0 0 0 0 1 1 0 0 0 0
0 1 1 0 1 0 0 0 0 0 0 0 0 0 0 1 1 0 1 0 1 1 1 0 1 0 0 0 0 1 1 0 1 0 0 0 1
1 0 1]
[1 0 0 0 1 1 1 1 0 0 0 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 1 1 1 0 1 0 0 1 1
0 0 1 0 0 0 1 0 0 0 0 0 0 1 0 1 0 0 1 0 0 0 0 0 1 0 1 1 0 0 0 0 1 0 0 1 0
0 1 0]
[0 0 0 0 0 0 1 0 0 1 0 1 0 0 0 1 0 0 0 1 0 0 0 0 1 0 0 1 1 0 1 1 0 0 0 0 0
1 0 0 0 0 0 0 0 0 0 1 0 1 0 1 1 1 0 1 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 0
0 0 0]
[0 0 0 1 0 0 1 0 0 1 0 0 0 0 1 0 0 0 0 1 0 0 0 1 1 0 0 1 0 0 0 0 1 0 0 0 0
0 0 1 1 0 1 0 0 0 0 0 0 0 1 1 0 0 0 1 0 0 0 0 1 0 0 0 0 0 0 0 1 0 1 0 0 1
1 0 0]
[0 0 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 1 0 1 0 0 0 0 0 1 0 0 1
1 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 1 1 1 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 1
0 0 0]
[0 0 0 0 0 0 1 1 0 1 1 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0 0 0 0 1 0 0 0 0 0 0 0
0 0 0 1 1 0 1 0 0 0 1 0 1 0 1 0 0 0 0 1 0 0 1 0 0 0 0 1 1 0 1 0 0 0 0 1 1
0 1 0]
[0 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 0 0 0 0
0 0 1 0 0 1 0 1 1 1 1 0 0 1 0 0 1 1 0 0 1 0 1 1 0 0 0 0 1 0 0 0 0 0 0 0 1
0 1]
[0 1 0 0 1 0 0 1 0 0 1 1 0 0 0 0 1 0 0 0 1 0 0 1 1 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 1 0 0 0 0 0 0 0 1 0 0 1 1 0 1 0 1 1 1 0 0 1 1 0 0 0 0 1 0 1 0 0 0 0
0 0]