Skip to content

Fix api changes for v12 for the strings blog #270

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

Open
VibhuJawa wants to merge 7 commits into
base: 012audit
Choose a base branch
from
Open

Fix api changes for v12 for the strings blog #270

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
2bfb6e1
Merge pull request #250 from rapidsai/taureandyernv-colab-bulletin
taureandyernv Nov 28, 2019
3bbf5a9
Merge pull request #251 from rapidsai/taureandyernv-colab-bulletin
taureandyernv Nov 28, 2019
2df0b26
Merge pull request #252 from rapidsai/taureandyernv-colab-bulletin
taureandyernv Nov 28, 2019
7c3ceb7
Merge pull request #254 from rapidsai/taureandyernv-colab-bulletin
taureandyernv Nov 28, 2019
6458bb1
fix api call for v12
VibhuJawa Jan 23, 2020
70732ed
fix typos
VibhuJawa Jan 23, 2020
0c5f943
1 last typo
VibhuJawa Jan 23, 2020
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
26 changes: 16 additions & 10 deletions blog_notebooks/nlp/show_me_the_word_count_gutenberg/show_me_the_word_count_gutenberg.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -191,7 +191,13 @@
"df = df.drop(labels=['label'])\n",
"\n",
"print(\"Number of lines in the DF = {:,}\".format(len(df)))\n",
"df.head(5).to_pandas()"
"df.head(5).to_pandas()\n",
"\n",
"## keeping only 90% because of the books\n",
"## because of temporary 1.5x overhead \n",
"## introduced in 0.12\n",
"## this will away with 0.13\n",
"df = df.head(int(len(df)*0.90))"
]
},
{
Expand Down Expand Up @@ -328,7 +334,7 @@
"metadata": {},
"outputs": [],
"source": [
"text_col_sample['text_clean'] = nvtext.replace_tokens(text_col_sample['text_clean'].data, STOPWORDS, ' ')\n",
"text_col_sample['text_clean'] = nvtext.replace_tokens(text_col_sample['text_clean']._column.nvstrings, STOPWORDS, ' ')\n",
"text_col_sample['text_clean'].to_pandas()"
]
},
Expand Down Expand Up @@ -394,7 +400,7 @@
" \n",
" # remove stopwords\n",
" stopwords_gpu = nvstrings.to_device(stopwords)\n",
" input_strs = nvtext.replace_tokens(input_strs.data, stopwords_gpu, ' ')\n",
" input_strs = nvtext.replace_tokens(input_strs._column.nvstrings, stopwords_gpu, ' ')\n",
" input_strs = cudf.Series(input_strs)\n",
" \n",
" # replace multiple spaces with single one and strip leading/trailing spaces\n",
Expand Down Expand Up @@ -464,7 +470,7 @@
" df = cudf.DataFrame()\n",
" # tokenize sentences into a string using nvtext.tokenize()\n",
" # it into a single tall data-frame\n",
" df['string'] = nvtext.tokenize(str_col.data)\n",
" df['string'] = nvtext.tokenize(str_col._column.nvstrings)\n",
" \n",
" # Using Group by to do a value count for string columns\n",
" # This will be natively supported soon\n",
Expand Down Expand Up @@ -634,8 +640,8 @@
" \"\"\"\n",
" import rmm\n",
" \n",
" cat = nvcategory.from_strings(str_s.data).set_keys(keys)\n",
" device_array = rmm.device_array(str_s.data.size(), dtype=np.int32) \n",
" cat = nvcategory.from_strings(str_s._column.nvstrings).set_keys(keys)\n",
" device_array = rmm.device_array(str_s._column.nvstrings.size(), dtype=np.int32) \n",
" cat.values(devptr=device_array.device_ctypes_pointer.value)\n",
" \n",
" return cudf.Series(device_array)\n",
Expand Down Expand Up @@ -674,7 +680,7 @@
"%%time\n",
"# keep only top 20k words in the dataset\n",
"th = 20_000\n",
"keys = count_df['string'][:th].data\n",
"keys = count_df['string'][:th]._column.nvstrings\n",
"encoded_wc_ls = []\n",
"\n",
"for auth_wc_df in author_wc_ls:\n",
Expand Down Expand Up @@ -805,8 +811,8 @@
" count_sr = encoded_wc_df['counts']\n",
" token_id_sr = encoded_wc_df['encoded_str_id']\n",
" \n",
" count_ar = count_sr.data.to_gpu_array()\n",
" token_id_ar = token_id_sr.data.to_gpu_array()\n",
" count_ar = count_sr.to_gpu_array()\n",
" token_id_ar = token_id_sr.to_gpu_array()\n",
" author_ar = count_dary[author_id]\n",
" \n",
" # See https://numba.pydata.org/numba-doc/0.13/CUDAJit.html\n",
Expand Down Expand Up @@ -1015,7 +1021,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
"version": "3.7.6"
}
},
"nbformat": 4,
Expand Down