Skip to content

remove all nb in:[] markups, pep8 strong enforce for ch-N #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mlkimmins merged 2 commits into from
Jun 29, 2023
Merged

remove all nb in:[] markups, pep8 strong enforce for ch-N #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
edb73b7
remove all nb in:[] markups, pep8 strong enforce for ch-N
Jun 29, 2023
9376a6d
redo whitespace pep8 trailing blank lines
Jun 29, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 1 addition & 4 deletions dask/Apppendix-A.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#!/usr/bin/env python
# coding: utf-8

# In[ ]:



# In[1]:
Expand All @@ -25,6 +25,3 @@
from dask.distributed import progress
futs = client.map(sleep, range(0, 100))
progress(futs)


# In[ ]:
72 changes: 36 additions & 36 deletions dask/Dask-Ch10_porting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,21 +1,21 @@
#!/usr/bin/env python
# coding: utf-8

# In[ ]:



# !pip install dask-yarn


# In[ ]:



# !conda install -c conda-forge dask-yarn
# import sys
# sys.version


# In[ ]:



#tag::ex_yarn_deployment[]
Expand All @@ -37,10 +37,10 @@
#end::ex_yarn_deployment[]


# In[ ]:


# In[ ]:




#tag::ex_slurm_deployment[]
Expand All @@ -63,10 +63,10 @@
#end::ex_slurm_deployment[]


# In[ ]:


# In[ ]:




#tag::ex_s3_minio_rw[]
Expand Down Expand Up @@ -98,24 +98,24 @@
#end::ex_s3_minio_rw[]


# In[ ]:


# In[ ]:




# !pip install fugue
# ! pip install antlr==4.10.1
# !pip install antlr4-python3-runtime==4.10.1


# In[ ]:


# In[ ]:


# In[ ]:





# !pip install fugue
Expand All @@ -124,19 +124,19 @@
# !conda install aiohttp


# In[ ]:


# In[ ]:


# In[ ]:





from fugue import transform


# In[ ]:



from fugue_notebook import setup
Expand All @@ -146,23 +146,23 @@
pass


# In[ ]:


# In[ ]:




import dask.dataframe as dd


# In[ ]:



url = 'https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2018-01.parquet'
df = dd.read_parquet(url)


# In[ ]:



#tag::ex_fugue_SQL[]
Expand All @@ -181,10 +181,10 @@
#end::ex_fugue_SQL[]


# In[ ]:


# In[ ]:




from fugue_notebook import setup
Expand All @@ -193,7 +193,7 @@
df = dd.read_parquet(url)


# In[ ]:



get_ipython().run_cell_magic(
Expand All @@ -202,10 +202,10 @@
'tempdf = SELECT VendorID, AVG(total_amount) AS average_fare FROM df GROUP BY VendorID\n\nSELECT *\nFROM tempdf\nORDER BY average_fare DESC\nLIMIT 5\nPRINT')


# In[ ]:


# In[ ]:




#tag::ex_postgres_dataframe[]
Expand All @@ -214,7 +214,7 @@
#end::ex_postgres_dataframe[]


# In[ ]:



#tag::ex_basic_logging[]
Expand All @@ -226,13 +226,13 @@
#end::ex_basic_logging[]


# In[ ]:


# In[ ]:


# In[ ]:





import numpy as np
Expand All @@ -243,7 +243,7 @@
from dask.distributed import Client, LocalCluster


# In[ ]:



# just sanity closing older client
Expand All @@ -252,7 +252,7 @@
client = Client(cluster) # Connect to distributed cluster and override default


# In[ ]:



#tag::ex_distributed_logging[]
Expand Down Expand Up @@ -291,16 +291,16 @@ def compute_softmax(partition, axis=0):
#end::ex_distributed_logging[]


# In[ ]:


# In[ ]:




# client.get_worker_logs()


# In[ ]:



# plain version of the function
Expand All @@ -324,10 +324,10 @@ def compute_softmax(x, axis=0):
scores_df.apply(compute_softmax, axis=1, meta=object).compute()


# In[ ]:


# In[ ]:




client.close()
27 changes: 12 additions & 15 deletions dask/Dask-Ch11_ML.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,10 +28,10 @@
# !pip install xgboost


# In[ ]:


# In[ ]:




# In[4]:
Expand Down Expand Up @@ -140,7 +140,7 @@
#end::ex_plot_distances


# In[ ]:



# In[19]:
Expand All @@ -151,7 +151,7 @@
df['trip_distance'].values.compute_chunk_sizes()


# In[ ]:



# In[20]:
Expand Down Expand Up @@ -211,7 +211,7 @@
plt.show()


# In[ ]:



# In[25]:
Expand All @@ -220,7 +220,7 @@
df['log_trip_duration'] = np.log(df['trip_duration'])


# In[ ]:



plt.hist(df['log_trip_duration'], bins=100)
Expand All @@ -230,7 +230,7 @@
sns.distplot(df["log_trip_duration"], bins=100)


# In[ ]:



# In[30]:
Expand Down Expand Up @@ -436,7 +436,7 @@
plt.show()


# In[ ]:



train_final = train.drop(['VendorID',
Expand Down Expand Up @@ -473,7 +473,7 @@
# In[2]:


# In[ ]:



# Just like standard xgb Dmatrix, but note that we are explicitly passing
Expand Down Expand Up @@ -523,7 +523,7 @@ def load_model(path):
# In[63]:


# In[ ]:

#tag::Dask_DataFrame_map_partition_inference[]
import dask.dataframe as dd
import dask.bag as db
Expand All @@ -546,10 +546,10 @@ def partition_operation(df):
#end::Dask_DataFrame_map_partition_inference


# In[ ]:


# In[ ]:




#tag::batched_operations[]
Expand Down Expand Up @@ -584,6 +584,3 @@ def handle_partition(df):
results = ddf.map_partitions(handle_partition)
results.compute()
#end::batched_operations


# In[ ]:
Loading