Applying TextBlob sentimental analysis to Twitter Stream - twitter

I am currently streaming tweets and want to apply sentimental analysis for each tweet, mapping both the tweet and the value. I keep getting an error: "NoneType' object has no attribute 'limit'". Not sure what I am doing wrong.
from textblob import TextBlob
from textblob import Blobber
from textblob.sentiments import NaiveBayesAnalyzer
tb = Blobber(analyzer=NaiveBayesAnalyzer())
def tweet_sentiment(tweet):
'''function for polarity'''
sentiment = tb(tweet)
if analysis.sentiment.polarity > .5:
return 1
elif analysis.sentiment.polarity < .5:
return -1
else:
return 0
(lines.flatMap(lambda x: (x, tweet_sentiment))
.map(lambda rec: Tweet(rec[0], rec[1]))
.foreachRDD(lambda rdd: rdd.toDF())
.limit(20).registerTempTable("tweets"))
-------------------------------------------------------------------
--------
AttributeError Traceback (most recent
call last)
<ipython-input-8-d939b88ef526> in <module>()
2 (lines.flatMap(lambda x: (x, tweet_sentiment))
3 .map(lambda rec: Tweet(rec[0], rec[1]))
----> 4 .foreachRDD(lambda rdd: rdd.toDF())
5 .limit(20).registerTempTable("tweets"))
AttributeError: 'NoneType' object has no attribute 'limit'

Try this:
(lines.flatMap(lambda x: (x, tweet_sentiment))
.map(lambda rec: Tweet(rec[0], rec[1]))
.foreachRDD(lambda rdd: rdd.toDF())
.registerTempTable("tweets"))

Related

show the visualization of the dataset before and after classification

Kindly, I am trying to create an ML model using SVM using a dataset with 23 features and the output should be (0 or 1) which means two classes. My Target to show the visualization before and after the classification.
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
ds= pd.read_csv("dataset_sdn.csv")
ds= ds.fillna(0)
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
X_Train, X_Test, Y_Train, Y_Test = train_test_split (X, Y, test_size=0.25, random_state=0)
sc_X = StandardScaler()
X_Train = sc_X.fit_transform(X_Train)
X_Test = sc_X.transform(X_Test)
Then i tried to visualization the X and Y
import matplotlib.pyplot as plt
plt.scatter(X,Y)
plt.show()
But i got error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [11], in <cell line: 2>()
1 import matplotlib.pyplot as plt
----> 2 plt.scatter(X,Y)
3 plt.show()
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\pyplot.py:2817, in scatter(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, data, **kwargs) 2812 #_copy_docstring_and_deprecators(Axes.scatter) 2813 def scatter( 2814 x, y, s=None, c=None, marker=None, cmap=None, norm=None, 2815 vmin=None, vmax=None, alpha=None, linewidths=None, *, 2816 edgecolors=None, plotnonfinite=False, data=None,
**kwargs):
-> 2817 __ret = gca().scatter( 2818 x, y, s=s, c=c, marker=marker, cmap=cmap, norm=norm, 2819 vmin=vmin, vmax=vmax, alpha=alpha, linewidths=linewidths, 2820 edgecolors=edgecolors, plotnonfinite=plotnonfinite, 2821
**({"data": data} if data is not None else {}), **kwargs) 2822 sci(__ret) 2823 return __ret
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\__init__.py:1414, in _preprocess_data.<locals>.inner(ax, data, *args, **kwargs) 1411 #functools.wraps(func) 1412 def inner(ax, *args, data=None,
**kwargs): 1413 if data is None:
-> 1414 return func(ax, *map(sanitize_sequence, args), **kwargs) 1416 bound = new_sig.bind(ax, *args, **kwargs) 1417 auto_label = (bound.arguments.get(label_namer) 1418 or bound.kwargs.get(label_namer))
File ~\AppData\Roaming\Python\Python310\site-packages\matplotlib\axes\_axes.py:4368, in Axes.scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, edgecolors, plotnonfinite, **kwargs) 4366 y = np.ma.ravel(y) 4367 if x.size != y.size:
-> 4368 raise ValueError("x and y must be the same size") 4370 if s is None: 4371 s = (20 if rcParams['_internal.classic_mode'] else 4372 rcParams['lines.markersize'] ** 2.0)
ValueError: x and y must be the same size
Then i start the classification
classifier = SVC (kernel='rbf', C=1, random_state=0,)
classifier.fit(X_Train, Y_Train)
Y_pred = classifier.predict(X_Test)
print (Y_pred)
The I tried to use below code but not work
from mlxtend.plotting import plot_decision_regions
plot_decision_regions(X=X_Test, y=Y_Test, clf=classifier, legend=1)
I get this error
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Input In [10], in <cell line: 2>()
1 from mlxtend.plotting import plot_decision_regions
----> 2 plot_decision_regions(X=Y_Test, y=X_Test, clf=classifier,legend=2)
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\plotting\decision_regions.py:148, in plot_decision_regions(X, y, clf, feature_index, filler_feature_values, filler_feature_ranges, ax, X_highlight, zoom_factor, legend, hide_spines, markers, colors, scatter_kwargs, contourf_kwargs, contour_kwargs, scatter_highlight_kwargs)
44 def plot_decision_regions(
45 X,
46 y, (...)
65 scatter_highlight_kwargs=None,
66 ):
67 """Plot decision regions of a classifier.
68
69 Please note that this functions assumes that class labels are (...)
145
146 """
--> 148 check_Xy(X, y, y_int=True) # Validate X and y arrays
149 dim = X.shape[1]
151 if ax is None:
File ~\AppData\Local\Programs\Python\Python310\lib\site-packages\mlxtend\utils\checking.py:16, in check_Xy(X, y, y_int)
12 def check_Xy(X, y, y_int=True):
13
14 # check types
15 if not isinstance(X, np.ndarray):
---> 16 raise ValueError("X must be a NumPy array. Found %s" % type(X))
17 if not isinstance(y, np.ndarray):
18 raise ValueError("y must be a NumPy array. Found %s" % type(y))
ValueError: X must be a NumPy array. Found <class 'pandas.core.series.Series'>
So, please your advice to how show the visualization. Thanks in advance
See here:
X = ds.iloc[: , [4,5,6,7,8,9,10,11,12,13,14,17,18,19,20,21]] # Input Features
Y = ds.iloc[:, 22] # OutPut
and then here
plt.scatter(X,Y)
Your X vector is multi-dimensional vector having a size of 16 and hence the scatterplot is not working. You can only plot 2 variables in a 2D scatterplot.
So you have plot for each feature vs Y, e.g.,
plt.scatter(X.iloc[:,0], Y)

Map Dask bincount over 2d array columns

I am trying to use bincount over a 2D array. Specifically I have this code:
import numpy as np
import dask.array as da
def dask_bincount(weights, x):
da.bincount(x, weights)
idx = da.random.random_integers(0, 1024, 1000)
weight = da.random.random((1000, 2))
bin_count = da.apply_along_axis(dask_bincount, 1, weight, idx)
The idea is that the bincount can be made with the same idx array on each one of the weight columns. That would return an array of size (np.amax(x) + 1, 2) if I am correct.
However when doing this I get this error message:
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-17-5b8eed89ad32> in <module>
----> 1 bin_count = da.apply_along_axis(dask_bincount, 1, weight, idx)
~/.local/lib/python3.9/site-packages/dask/array/routines.py in apply_along_axis(func1d, axis, arr, dtype, shape, *args, **kwargs)
454 if shape is None or dtype is None:
455 test_data = np.ones((1,), dtype=arr.dtype)
--> 456 test_result = np.array(func1d(test_data, *args, **kwargs))
457 if shape is None:
458 shape = test_result.shape
<ipython-input-14-34fd0eb9b775> in dask_bincount(weights, x)
1 def dask_bincount(weights, x):
----> 2 da.bincount(x, weights)
~/.local/lib/python3.9/site-packages/dask/array/routines.py in bincount(x, weights, minlength, split_every)
670 raise ValueError("Input array must be one dimensional. Try using x.ravel()")
671 if weights is not None:
--> 672 if weights.chunks != x.chunks:
673 raise ValueError("Chunks of input array x and weights must match.")
674
AttributeError: 'numpy.ndarray' object has no attribute 'chunks'
I thought that when dask array were created the library automatically assigns them chunks, so the error does not say much. How can I fix this?
I made an script that does it on numpy with map.
idx_np = np.random.randint(0, 1024, 1000)
weight_np = np.random.random((1000,2))
f = lambda y: np.bincount(idx_np, weight_np[:,y])
result = map(f, [i for i in range(2)])
np.array(list(result))
array([[0.9885341 , 0.9977873 , 0.24937023, ..., 0.31024526, 1.40754883,
0.87609759],
[1.77406303, 0.84787723, 0.14591474, ..., 0.54584068, 0.38357015,
0.85202672]])
I would like to the same but with dask
There are multiple problems at play.
Weights should be (2, 1000)
You discover this by trying to write the same function in numpy using apply_along_axis.
idx_np = np.random.random_integers(0, 1024, 1000)
weight_np = np.random.random((2, 1000)) # <- transposed
# This gives the same result as the code you provided
np.apply_along_axis(lambda weight, idx: np.bincount(idx, weight), 1, weight_np, idx_np)
da.apply_along_axis applies the function to numpy arrays
You're getting the error
AttributeError: 'numpy.ndarray' object has no attribute 'chunks'
This suggests that what makes it into the da.bincount method is actually a numpy array. The fact is that da.apply_along_axis actually takes each row of weight and sends it to the function as a numpy array.
Your function should therefore actually be a numpy function:
def bincount(weights, x):
return np.bincount(x, weights)
However, if you try this, you will still get the same error. I believe that happens for a whole another reason though:
Dask doesn't know what the output shape will be and tries to infer it
In the code and/or documentation for apply_along_axis, we can see that Dask tries to infer the output shape and dtype by passing in the array [1] (related question). This is a problem, since bincount cannot just accept such argument.
What we can do instead is provide shape and dtype to the method so that Dask doesn't have to infer it.
The problem here is that bincount's output shape depends on the maximum value of the input array. Unless you know it beforehand, you will sadly need to compute it. The whole operation therefore won't be fully lazy.
This is the full answer:
import numpy as np
import dask.array as da
idx = da.random.random_integers(0, 1024, 1000)
weight = da.random.random((2, 1000))
def bincount(weights, x):
return np.bincount(x, weights)
m = idx.max().compute()
da.apply_along_axis(bincount, 1, weight, idx, shape=(m,), dtype=weight.dtype)
Appendix: randint vs random_integers
Be careful, because these are subtly different
randint takes integers from low (inclusive) to high (exclusive)
random_integers takes integers from low (inclusive) to high (inclusive)
Thus you have to call randint with high + 1 to get the same value.

sklearn oneclass svm KeyError

My Dataset is a set of system calls for both malware and benign, I preprocessed it and now it looks like this
NtQueryPerformanceCounter
NtProtectVirtualMemory
NtProtectVirtualMemory
NtQuerySystemInformation
NtQueryVirtualMemory
NtQueryVirtualMemory
NtProtectVirtualMemory
NtOpenKey
NtOpenKey
NtOpenKey
NtQuerySecurityAttributesToken
NtQuerySecurityAttributesToken
NtQuerySystemInformation
NtQuerySystemInformation
NtAllocateVirtualMemory
NtFreeVirtualMemory
Now I'm using tfidf to extract the features and then use ngram to make a sequence of them
from __future__ import print_function
import numpy as np
import pandas as pd
from time import time
import matplotlib.pyplot as plt
from sklearn import svm, datasets
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.utils import shuffle
from sklearn.svm import OneClassSVM
nGRAM1 = 8
nGRAM2 = 10
weight = 4
main_corpus_MAL = []
main_corpus_target_MAL = []
main_corpus_BEN = []
main_corpus_target_BEN = []
my_categories = ['benign', 'malware']
# feeding corpus the testing data
print("Loading system call database for categories:")
print(my_categories if my_categories else "all")
import glob
import os
malCOUNT = 0
benCOUNT = 0
for filename in glob.glob(os.path.join('C:\\Users\\alika\\Documents\\testingSVM\\sysMAL', '*.txt')):
fMAL = open(filename, "r")
aggregate = ""
for line in fMAL:
linea = line[:(len(line)-1)]
aggregate += " " + linea
main_corpus_MAL.append(aggregate)
main_corpus_target_MAL.append(1)
malCOUNT += 1
for filename in glob.glob(os.path.join('C:\\Users\\alika\\Documents\\testingSVM\\sysBEN', '*.txt')):
fBEN = open(filename, "r")
aggregate = ""
for line in fBEN:
linea = line[:(len(line) - 1)]
aggregate += " " + linea
main_corpus_BEN.append(aggregate)
main_corpus_target_BEN.append(0)
benCOUNT += 1
# weight as determined in the top of the code
train_corpus = main_corpus_BEN[:(weight*len(main_corpus_BEN)//(weight+1))]
train_corpus_target = main_corpus_target_BEN[:(weight*len(main_corpus_BEN)//(weight+1))]
test_corpus = main_corpus_MAL[(len(main_corpus_MAL)-(len(main_corpus_MAL)//(weight+1))):]
test_corpus_target = main_corpus_target_MAL[(len(main_corpus_MAL)-len(main_corpus_MAL)//(weight+1)):]
def size_mb(docs):
return sum(len(s.encode('utf-8')) for s in docs) / 1e6
# size of datasets
train_corpus_size_mb = size_mb(train_corpus)
test_corpus_size_mb = size_mb(test_corpus)
print("%d documents - %0.3fMB (training set)" % (
len(train_corpus_target), train_corpus_size_mb))
print("%d documents - %0.3fMB (test set)" % (
len(test_corpus_target), test_corpus_size_mb))
print("%d categories" % len(my_categories))
print()
print("Benign Traces: "+str(benCOUNT)+" traces")
print("Malicious Traces: "+str(malCOUNT)+" traces")
print()
print("Extracting features from the training data using a sparse vectorizer...")
t0 = time()
vectorizer = TfidfVectorizer(ngram_range=(nGRAM1, nGRAM2), min_df=1, use_idf=True, smooth_idf=True) ##############
analyze = vectorizer.build_analyzer()
X_train = vectorizer.fit_transform(train_corpus)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, train_corpus_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_train.shape)
print()
print("Extracting features from the test data using the same vectorizer...")
t0 = time()
X_test = vectorizer.transform(test_corpus)
duration = time() - t0
print("done in %fs at %0.3fMB/s" % (duration, test_corpus_size_mb / duration))
print("n_samples: %d, n_features: %d" % X_test.shape)
print()
The output is:
Loading system call database for categories:
['benign', 'malware']
177 documents - 45.926MB (training set)
44 documents - 12.982MB (test set)
2 categories
Benign Traces: 72 traces
Malicious Traces: 150 traces
Extracting features from the training data using a sparse vectorizer...
done in 7.831695s at 5.864MB/s
n_samples: 177, n_features: 603170
Extracting features from the test data using the same vectorizer...
done in 1.624100s at 7.993MB/s
n_samples: 44, n_features: 603170
Now for the learning section I'm trying to use sklearn OneClassSVM:
print("==================\n")
print("Training: ")
classifier = OneClassSVM(kernel='linear', gamma='auto')
classifier.fit(X_test)
fraud_pred = classifier.predict(X_test)
unique, counts = np.unique(fraud_pred, return_counts=True)
print (np.asarray((unique, counts)).T)
fraud_pred = pd.DataFrame(fraud_pred)
fraud_pred= fraud_pred.rename(columns={0: 'prediction'})
main_corpus_target = pd.DataFrame(main_corpus_target)
main_corpus_target= main_corpus_target.rename(columns={0: 'Category'})
this the output to fraud_pred and main_corpus_target
prediction
0 1
1 -1
2 1
3 1
4 1
5 -1
6 1
7 -1
...
30 rows * 1 column
====================
Category
0 1
1 1
2 1
3 1
4 1
...
217 0
218 0
219 0
220 0
221 0
222 rows * 1 column
but when i try to calculate TP,TN,FP,FN:
##Performance check of the model
TP = FN = FP = TN = 0
for j in range(len(main_corpus_target)):
if main_corpus_target['Category'][j]== 0 and fraud_pred['prediction'][j] == 1:
TP = TP+1
elif main_corpus_target['Category'][j]== 0 and fraud_pred['prediction'][j] == -1:
FN = FN+1
elif main_corpus_target['Category'][j]== 1 and fraud_pred['prediction'][j] == 1:
FP = FP+1
else:
TN = TN +1
print (TP, FN, FP, TN)
I get this error:
KeyError Traceback (most recent call last)
<ipython-input-32-1046cc75ba83> in <module>
7 elif main_corpus_target['Category'][j]== 0 and fraud_pred['prediction'][j] == -1:
8 FN = FN+1
----> 9 elif main_corpus_target['Category'][j]== 1 and fraud_pred['prediction'][j] == 1:
10 FP = FP+1
11 else:
c:\users\alika\appdata\local\programs\python\python36\lib\site-packages\pandas\core\series.py in __getitem__(self, key)
1069 key = com.apply_if_callable(key, self)
1070 try:
-> 1071 result = self.index.get_value(self, key)
1072
1073 if not is_scalar(result):
c:\users\alika\appdata\local\programs\python\python36\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
4728 k = self._convert_scalar_indexer(k, kind="getitem")
4729 try:
-> 4730 return self._engine.get_value(s, k, tz=getattr(series.dtype, "tz", None))
4731 except KeyError as e1:
4732 if len(self) > 0 and (self.holds_integer() or self.is_boolean()):
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()
KeyError: 30
1) I know the error is because it's trying to access a key that isn’t in a dictionary, but i can't just insert some numbers in the fraud_pred to handle this issue, any suggestions??
2) Am i doing anything wrong that they don't match?
3) I want to compare the results to other one class classification algorithms, Due to my method, what are the best ones that i can use??
Edit: Before calculating the metrics:
You could change your fit and predict functions to:
fraud_pred = classifier.fit_predict(X_test)
Also, your main_corpus_target and X_test should have the same length, can you put the code where you create main_corpus_target please?
its created it right after the benCOUNT += 1:
main_corpus_target = main_corpus_target_MAL main_corpus_target.extend(main_corpus_target_BEN)
This means that you are creating a main_corpus_target that includes MAL and BEN, and the error you get is:
ValueError: Found input variables with inconsistent numbers of samples: [30, 222]
The number of samples of fraud_pred is 30, so you should evaluate them with an array of 30. main_corpus_target contains 222.
Watching your code, I see that you want to evaluate the X_test, which is related to test_corpus X_test = vectorizer.transform(test_corpus). It would be better to compare your results to test_corpus_target, which is the target variable of your dataset and also has a length of 30.
These two lines that you have should output the same length:
test_corpus = main_corpus_MAL[(len(main_corpus_MAL)-(len(main_corpus_MAL)//(weight+1))):]
test_corpus_target = main_corpus_target_MAL[(len(main_corpus_MAL)-len(main_corpus_MAL)//(weight+1)):]
May I ask why are you calculating the TP, TN... by yourself?
You have a faster option:
Transform the fraud_pred series, replacing the -1 to 0.
Use the confusion matrix function that sklearn offers.
Use ravel to extract the values of the confusion matrix.
An example, after transforming the -1 to 0:
from sklearn.metrics import confusion_matrix
tn, fp, fn, tp = confusion_matrix(fraud_pred, main_corpus_target['Category'].values).ravel()
Also, if you are using the last pandas version:
from sklearn.metrics import confusion_matrix
tn, fp, fn, tp = confusion_matrix(fraud_pred, main_corpus_target['Category'].to_numpy()).ravel()

How to use sklearn.inspection.permutation_importance for clustering algorithm

import numpy as np
from sklearn.datasets import make_classification
from sklearn.cluster import KMeans
X, y = make_classification(n_samples=1000,
n_features=4,
n_informative=3,
n_redundant=0,
n_repeated=0,
n_classes=2,
random_state=0,
shuffle=False)
km = KMeans(n_clusters=3).fit(X)
result = permutation_importance(km, X, y, scoring='homogeneity_score', n_repeats=10, random_state=0, n_jobs=-1)
result
In the real problem, I don't have y (true label), I tried to do y=None to make it as an unsupervised learning. But it does not work. I got:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-72-81045ae9cb66> in <module>()
----> 1 result = permutation_importance(km, X, y=None, scoring='homogeneity_score', n_repeats=10, random_state=0, n_jobs=-1)
5 frames
/usr/local/lib/python3.6/dist-packages/sklearn/metrics/cluster/_supervised.py in check_clusterings(labels_true, labels_pred)
53 if labels_true.ndim != 1:
54 raise ValueError(
---> 55 "labels_true must be 1D: shape is %r" % (labels_true.shape,))
56 if labels_pred.ndim != 1:
57 raise ValueError(
ValueError: labels_true must be 1D: shape is ()
Do anyone know how to implement without true label?
First of all, it is trivial to prove that k-means is invariant to a permutation of features... Because the sum is permutation invariant.
If you still want to experiment, try using an array of 0s as y maybe?

How to do groupby filter in Dask

I am attempting to take a dask dataframe, group by column 'A' and remove the groups where there are fewer than MIN_SAMPLE_COUNT rows.
For example, the following code works in pandas:
import pandas as pd
import dask as da
MIN_SAMPLE_COUNT = 1
x = pd.DataFrame([[1,2,3], [1,5,6], [2,8,9], [1,3,5]])
x.columns = ['A', 'B', 'C']
grouped = x.groupby('A')
x = grouped.filter(lambda x: x['A'].count().astype(int) > MIN_SAMPLE_COUNT)
However, in Dask if I try something analogous:
import pandas as pd
import dask
MIN_SAMPLE_COUNT = 1
x = pd.DataFrame([[1,2,3], [1,5,6], [2,8,9], [1,3,5]])
x.columns = ['A', 'B', 'C']
x = dask.dataframe.from_pandas(x, npartitions=2)
grouped = x.groupby('A')
x = grouped.filter(lambda x: x['A'].count().astype(int) > MIN_SAMPLE_COUNT)
I get the following error message:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\dataframe\groupby.py in __getattr__(self, key)
1162 try:
-> 1163 return self[key]
1164 except KeyError as e:
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\dataframe\groupby.py in __getitem__(self, key)
1153 # error is raised from pandas
-> 1154 g._meta = g._meta[key]
1155 return g
~\AppData\Local\Continuum\anaconda3\lib\site-packages\pandas\core\base.py in __getitem__(self, key)
274 if key not in self.obj:
--> 275 raise KeyError("Column not found: {key}".format(key=key))
276 return self._gotitem(key, ndim=1)
KeyError: 'Column not found: filter'
During handling of the above exception, another exception occurred:
AttributeError Traceback (most recent call last)
<ipython-input-55-d8a969cc041b> in <module>()
1 # Remove sixty second blocks that have fewer than MIN_SAMPLE_COUNT samples.
2 grouped = dat.groupby('KPI_60_seconds')
----> 3 dat = grouped.filter(lambda x: x['KPI_60_seconds'].count().astype(int) > MIN_SAMPLE_COUNT)
~\AppData\Local\Continuum\anaconda3\lib\site-packages\dask\dataframe\groupby.py in __getattr__(self, key)
1163 return self[key]
1164 except KeyError as e:
-> 1165 raise AttributeError(e)
1166
1167 #derived_from(pd.core.groupby.DataFrameGroupBy)
AttributeError: 'Column not found: filter'
The error message suggests that the filter method used in Pandas has not been implemented in Dask (nor did I find it after a search).
Is there a Dask functionality which captures what I am looking to do? I have gone through the Dask API and nothing stood out to me as what I need. I am currently using Dask '1.1.1'
Thank you for your help.
Fairly new to Dask myself. One way to achieve you are trying could be as follows:
Dask version: 0.17.3
import pandas as pd
import dask.dataframe as dd
MIN_SAMPLE_COUNT = 1
x = pd.DataFrame([[1,2,3], [1,5,6], [2,8,9], [1,3,5]])
x.columns = ['A', 'B', 'C']
print("x (before):")
print(x) # still pandas
x = dd.from_pandas(x, npartitions=2)
grouped = x.groupby('A').B.count().reset_index()
grouped = grouped.rename(columns={'B': 'Count'})
y = dd.merge(x, grouped, on=['A'])
y = y[y.Count > MIN_SAMPLE_COUNT]
x = y[['A', 'B', 'C']]
print("x (after):")
print(x.compute()) # needs compute for conversion to pandas df
Output:
x (before):
A B C
0 1 2 3
1 1 5 6
2 2 8 9
3 1 3 5
x (after):
A B C
0 1 2 3
1 1 5 6
1 1 3 5

Resources