Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import pandas as pd
- import os
- import glob
- from pathlib import Path
- import matplotlib
- import matplotlib.pylab as plt
- import missingno as msno
- df = pd.concat(map(lambda file: pd.read_csv(file,index_col=False), glob.glob(os.path.join(output_csv_path, "*.csv"))))
- missingdata_df = df.columns[df.isnull().any()].tolist()
- msno.matrix(df[missingdata_df])
- msno.heatmap(df[missingdata_df], figsize=(20,20))
- import dask
- import dask.dataframe as dd
- import pandas as pd
- import os
- import glob
- from pathlib import Path
- import matplotlib
- import matplotlib.pylab as plt
- import missingno as msno
- df= dd.read_csv('C:/Users/zeba.anjum/Documents/Output files/*.csv')
- missingdata_df = df.columns[df.isnull().any()].tolist()
- msno.matrix(df[missingdata_df])
- msno.heatmap(df[missingdata_df], figsize=(20,20))
- runfile('C:/Users/zeba.anjum/Documents/Python code/data_visualization_dask.py', wdir='C:/Users/zeba.anjum/Documents/Python code')
- Reloaded modules: UTCts_to_datetime
- Traceback (most recent call last):
- File "<ipython-input-8-a9679b2c04a9>", line 1, in <module>
- runfile('C:/Users/zeba.anjum/Documents/Python code/data_visualization_dask.py', wdir='C:/Users/zeba.anjum/Documents/Python code')
- File "C:Anacondalibsite-packagesspyderutilssitesitecustomize.py", line 705, in runfile
- execfile(filename, namespace)
- File "C:Anacondalibsite-packagesspyderutilssitesitecustomize.py", line 102, in execfile
- exec(compile(f.read(), filename, 'exec'), namespace)
- File "C:/Users/zeba.anjum/Documents/Python code/data_visualization_dask.py", line 34, in <module>
- msno.matrix(df[missingdata_df])
- File "C:Anacondalibsite-packagesmissingnomissingno.py", line 61, in matrix
- ax0.imshow(g, interpolation='none')
- File "C:Anacondalibsite-packagesmatplotlib__init__.py", line 1855, in inner
- return func(ax, *args, **kwargs)
- File "C:Anacondalibsite-packagesmatplotlibaxes_axes.py", line 5487, in imshow
- im.set_data(X)
- File "C:Anacondalibsite-packagesmatplotlibimage.py", line 645, in set_data
- self._A = cbook.safe_masked_invalid(A, copy=True)
- File "C:Anacondalibsite-packagesmatplotlibcbook__init__.py", line 1364, in safe_masked_invalid
- x = np.array(x, subok=True, copy=copy)
- MemoryError
- Traceback (most recent call last):
- File "<ipython-input-7-a9679b2c04a9>", line 1, in <module>
- runfile('C:/Users/zeba.anjum/Documents/Python code/data_visualization_dask.py', wdir='C:/Users/zeba.anjum/Documents/Python code')
- File "C:Anacondalibsite-packagesspyderutilssitesitecustomize.py", line 705, in runfile
- execfile(filename, namespace)
- File "C:Anacondalibsite-packagesspyderutilssitesitecustomize.py", line 102, in execfile
- exec(compile(f.read(), filename, 'exec'), namespace)
- File "C:/Users/zeba.anjum/Documents/Python code/data_visualization_dask.py", line 32, in <module>
- msno.matrix(df[missingdata_df])
- File "C:Anacondalibsite-packagesmissingnomissingno.py", line 40, in matrix
- height = df.shape[0]
- File "C:Anacondalibsite-packagesdaskdataframecore.py", line 2414, in __getattr__
- raise AttributeError("'DataFrame' object has no attribute %r" % key)
- AttributeError: 'DataFrame' object has no attribute 'shape'
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement