From 7b9b4235f471c9180f0029629022ddf228c49735 Mon Sep 17 00:00:00 2001 From: Kumar Apurva <66004696+KUMAR-APURVA@users.noreply.github.com> Date: Sun, 27 Jun 2021 12:25:46 +0530 Subject: [PATCH 1/2] [Ch2Nb06] Added dependencies and fixed some errors 1. Added pip install wget command. 2. Added pip install textblob command. 3. Fixed some errors. --- Ch2/06_Snorkel.ipynb | 863 ++++++++++++++++++++----------------------- 1 file changed, 392 insertions(+), 471 deletions(-) diff --git a/Ch2/06_Snorkel.ipynb b/Ch2/06_Snorkel.ipynb index 2c6da6a..7e8645a 100644 --- a/Ch2/06_Snorkel.ipynb +++ b/Ch2/06_Snorkel.ipynb @@ -3,7 +3,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "kBRUuq_poB7u" }, "source": [ @@ -23,138 +22,178 @@ "start_time": "2021-04-03T11:07:43.179631Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 940 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "1TqgrfwYNlbQ", - "outputId": "b0584485-e593-4768-f0aa-a6c84fe74244", - "scrolled": true + "outputId": "6dec4d9a-a86a-4be6-cbb2-5038f174ff25", + "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Requirement already satisfied: snorkel==0.9.6 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (0.9.6)\n", - "Requirement already satisfied: munkres>=1.0.6 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.1.4)\n", - "Requirement already satisfied: scipy<2.0.0,>=1.2.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.5.4)\n", - "Requirement already satisfied: tensorboard<2.0.0,>=1.14.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.15.0)\n", - "Requirement already satisfied: tqdm<5.0.0,>=4.33.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (4.59.0)\n", - "Requirement already satisfied: torch<2.0.0,>=1.2.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.8.1)\n", - "Requirement already satisfied: pandas<2.0.0,>=0.25.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.1.5)\n", - "Requirement already satisfied: scikit-learn<0.22.0,>=0.20.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (0.21.3)\n", - "Requirement already satisfied: networkx<2.4,>=2.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (2.3)\n", - "Requirement already satisfied: numpy<2.0.0,>=1.16.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from snorkel==0.9.6) (1.19.5)\n", - "Requirement already satisfied: decorator>=4.3.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from networkx<2.4,>=2.2->snorkel==0.9.6) (4.4.2)\n", - "Requirement already satisfied: python-dateutil>=2.7.3 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from pandas<2.0.0,>=0.25.0->snorkel==0.9.6) (2.8.1)\n", - "Requirement already satisfied: pytz>=2017.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from pandas<2.0.0,>=0.25.0->snorkel==0.9.6) (2021.1)\n", - "Requirement already satisfied: six>=1.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from python-dateutil>=2.7.3->pandas<2.0.0,>=0.25.0->snorkel==0.9.6) (1.15.0)\n", - "Requirement already satisfied: joblib>=0.11 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from scikit-learn<0.22.0,>=0.20.2->snorkel==0.9.6) (1.0.1)\n", - "Requirement already satisfied: werkzeug>=0.11.15 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (1.0.1)\n", - "Requirement already satisfied: setuptools>=41.0.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (54.1.2)\n", - "Requirement already satisfied: grpcio>=1.6.3 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (1.36.1)\n", - "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.3.4)\n", - "Requirement already satisfied: wheel>=0.26 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (0.36.2)\n", - "Requirement already satisfied: protobuf>=3.6.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.15.6)\n", - "Requirement already satisfied: absl-py>=0.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (0.12.0)\n", - "Requirement already satisfied: importlib-metadata in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from markdown>=2.6.8->tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.10.0)\n", - "Requirement already satisfied: typing-extensions in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from torch<2.0.0,>=1.2.0->snorkel==0.9.6) (3.7.4.3)\n", - "Requirement already satisfied: dataclasses in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from torch<2.0.0,>=1.2.0->snorkel==0.9.6) (0.8)\n", - "Requirement already satisfied: zipp>=0.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.4.1)\n", - "Requirement already satisfied: treedlib==0.1.3 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (0.1.3)\n", - "Requirement already satisfied: lxml in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from treedlib==0.1.3) (4.6.3)\n", - "Requirement already satisfied: numbskull==0.1.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (0.1.1)\n", - "Requirement already satisfied: future in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from numbskull==0.1.1) (0.18.2)\n", - "Requirement already satisfied: tensorflow==1.15 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (1.15.0)\n", - "Requirement already satisfied: wrapt>=1.11.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.12.1)\n", - "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.1.0)\n", - "Requirement already satisfied: astor>=0.6.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (0.8.1)\n", - "Requirement already satisfied: keras-applications>=1.0.8 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.0.8)\n", - "Requirement already satisfied: absl-py>=0.7.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (0.12.0)\n", - "Requirement already satisfied: six>=1.10.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.15.0)\n", - "Requirement already satisfied: tensorboard<1.16.0,>=1.15.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.15.0)\n", - "Requirement already satisfied: tensorflow-estimator==1.15.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.15.1)\n", - "Requirement already satisfied: protobuf>=3.6.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (3.15.6)\n", - "Requirement already satisfied: grpcio>=1.8.6 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.36.1)\n", - "Requirement already satisfied: wheel>=0.26 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (0.36.2)\n", - "Requirement already satisfied: gast==0.2.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (0.2.2)\n", - "Requirement already satisfied: keras-preprocessing>=1.0.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.1.2)\n", - "Requirement already satisfied: numpy<2.0,>=1.16.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (1.19.5)\n", - "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (3.3.0)\n", - "Requirement already satisfied: google-pasta>=0.1.6 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorflow==1.15) (0.2.0)\n", - "Requirement already satisfied: h5py in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from keras-applications>=1.0.8->tensorflow==1.15) (3.1.0)\n", - "Requirement already satisfied: werkzeug>=0.11.15 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (1.0.1)\n", - "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.3.4)\n", - "Requirement already satisfied: setuptools>=41.0.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (54.1.2)\n", - "Requirement already satisfied: importlib-metadata in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.10.0)\n", - "Requirement already satisfied: cached-property in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from h5py->keras-applications>=1.0.8->tensorflow==1.15) (1.5.2)\n", - "Requirement already satisfied: typing-extensions>=3.6.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.7.4.3)\n", - "Requirement already satisfied: zipp>=0.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.4.1)\n", - "Requirement already satisfied: tensorboard==1.15 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (1.15.0)\n", - "Requirement already satisfied: absl-py>=0.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (0.12.0)\n", - "Requirement already satisfied: protobuf>=3.6.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (3.15.6)\n", - "Requirement already satisfied: setuptools>=41.0.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (54.1.2)\n", - "Requirement already satisfied: six>=1.10.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (1.15.0)\n", - "Requirement already satisfied: werkzeug>=0.11.15 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (1.0.1)\n", - "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (3.3.4)\n", - "Requirement already satisfied: grpcio>=1.6.3 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (1.36.1)\n", - "Requirement already satisfied: wheel>=0.26 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (0.36.2)\n", - "Requirement already satisfied: numpy>=1.12.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from tensorboard==1.15) (1.19.5)\n", - "Requirement already satisfied: importlib-metadata in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from markdown>=2.6.8->tensorboard==1.15) (3.10.0)\n", - "Requirement already satisfied: zipp>=0.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard==1.15) (3.4.1)\n", - "Requirement already satisfied: typing-extensions>=3.6.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata->markdown>=2.6.8->tensorboard==1.15) (3.7.4.3)\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Collecting en-core-web-sm==3.0.0\n", - " Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.0.0/en_core_web_sm-3.0.0-py3-none-any.whl (13.7 MB)\n", - "Requirement already satisfied: spacy<3.1.0,>=3.0.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from en-core-web-sm==3.0.0) (3.0.5)\n", - "Requirement already satisfied: setuptools in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (54.1.2)\n", - "Requirement already satisfied: numpy>=1.15.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (1.19.5)\n", - "Requirement already satisfied: requests<3.0.0,>=2.13.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.25.1)\n", - "Requirement already satisfied: importlib-metadata>=0.20 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.10.0)\n", - "Requirement already satisfied: typer<0.4.0,>=0.3.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.3.2)\n", - "Requirement already satisfied: srsly<3.0.0,>=2.4.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.4.0)\n", - "Requirement already satisfied: blis<0.8.0,>=0.4.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.7.4)\n", - "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (4.59.0)\n", - "Requirement already satisfied: pydantic<1.8.0,>=1.7.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (1.7.3)\n", - "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (1.0.5)\n", - "Requirement already satisfied: wasabi<1.1.0,>=0.8.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.8.2)\n", - "Requirement already satisfied: typing-extensions<4.0.0.0,>=3.7.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.7.4.3)\n", - "Requirement already satisfied: packaging>=20.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (20.9)\n", - "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.0.5)\n", - "Requirement already satisfied: pathy>=0.3.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.4.0)\n", - "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.0.1)\n", - "Requirement already satisfied: jinja2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.11.3)\n", - "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.0.5)\n", - "Requirement already satisfied: thinc<8.1.0,>=8.0.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (8.0.2)\n", - "Requirement already satisfied: catalogue<2.1.0,>=2.0.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.0.1)\n", - "Requirement already satisfied: zipp>=0.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from importlib-metadata>=0.20->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.4.1)\n", - "Requirement already satisfied: pyparsing>=2.0.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from packaging>=20.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.4.7)\n", - "Requirement already satisfied: smart-open<4.0.0,>=2.2.0 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from pathy>=0.3.5->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (3.0.0)\n", - "Requirement already satisfied: dataclasses<1.0,>=0.6 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from pathy>=0.3.5->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.8)\n", - "Requirement already satisfied: idna<3,>=2.5 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.10)\n", - "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (1.26.4)\n", - "Requirement already satisfied: chardet<5,>=3.0.2 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (4.0.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from requests<3.0.0,>=2.13.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2020.12.5)\n", - "Requirement already satisfied: contextvars<3,>=2.4 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from thinc<8.1.0,>=8.0.2->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (2.4)\n", - "Requirement already satisfied: immutables>=0.9 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from contextvars<3,>=2.4->thinc<8.1.0,>=8.0.2->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (0.15)\n", - "Requirement already satisfied: click<7.2.0,>=7.1.1 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from typer<0.4.0,>=0.3.0->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (7.1.2)\n", - "Requirement already satisfied: MarkupSafe>=0.23 in c:\\users\\karti\\envs\\pnlp\\lib\\site-packages (from jinja2->spacy<3.1.0,>=3.0.0->en-core-web-sm==3.0.0) (1.1.1)\n", - "[+] Download and installation successful\n", - "You can now load the package via spacy.load('en_core_web_sm')\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "2021-04-03 16:37:49.144386: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_100.dll'; dlerror: cudart64_100.dll not found\n", - "2021-04-03 16:37:49.144410: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n" + "Collecting snorkel==0.9.6\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/4e/6a/e33babd8b4fb34867b695b5ab6b02c9106ec9de05ed4a02b2b9417eb3ae7/snorkel-0.9.6-py3-none-any.whl (144kB)\n", + "\u001b[K |████████████████████████████████| 153kB 30.6MB/s \n", + "\u001b[?25hRequirement already satisfied: tqdm<5.0.0,>=4.33.0 in /usr/local/lib/python3.7/dist-packages (from snorkel==0.9.6) (4.41.1)\n", + "Requirement already satisfied: scipy<2.0.0,>=1.2.0 in /usr/local/lib/python3.7/dist-packages (from snorkel==0.9.6) (1.4.1)\n", + "Collecting tensorboard<2.0.0,>=1.14.0\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/1e/e9/d3d747a97f7188f48aa5eda486907f3b345cd409f0a0850468ba867db246/tensorboard-1.15.0-py3-none-any.whl (3.8MB)\n", + "\u001b[K |████████████████████████████████| 3.8MB 29.7MB/s \n", + "\u001b[?25hCollecting munkres>=1.0.6\n", + " Downloading https://files.pythonhosted.org/packages/90/ab/0301c945a704218bc9435f0e3c88884f6b19ef234d8899fb47ce1ccfd0c9/munkres-1.1.4-py2.py3-none-any.whl\n", + "Collecting networkx<2.4,>=2.2\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/85/08/f20aef11d4c343b557e5de6b9548761811eb16e438cee3d32b1c66c8566b/networkx-2.3.zip (1.7MB)\n", + "\u001b[K |████████████████████████████████| 1.8MB 33.9MB/s \n", + "\u001b[?25hCollecting scikit-learn<0.22.0,>=0.20.2\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/9f/c5/e5267eb84994e9a92a2c6a6ee768514f255d036f3c8378acfa694e9f2c99/scikit_learn-0.21.3-cp37-cp37m-manylinux1_x86_64.whl (6.7MB)\n", + "\u001b[K |████████████████████████████████| 6.7MB 25.6MB/s \n", + "\u001b[?25hRequirement already satisfied: torch<2.0.0,>=1.2.0 in /usr/local/lib/python3.7/dist-packages (from snorkel==0.9.6) (1.9.0+cu102)\n", + "Requirement already satisfied: pandas<2.0.0,>=0.25.0 in /usr/local/lib/python3.7/dist-packages (from snorkel==0.9.6) (1.1.5)\n", + "Requirement already satisfied: numpy<2.0.0,>=1.16.0 in /usr/local/lib/python3.7/dist-packages (from snorkel==0.9.6) (1.19.5)\n", + "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.3.4)\n", + "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (0.12.0)\n", + "Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (0.36.2)\n", + "Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (1.15.0)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (57.0.0)\n", + "Requirement already satisfied: grpcio>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (1.34.1)\n", + "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (1.0.1)\n", + "Requirement already satisfied: protobuf>=3.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.12.4)\n", + "Requirement already satisfied: decorator>=4.3.0 in /usr/local/lib/python3.7/dist-packages (from networkx<2.4,>=2.2->snorkel==0.9.6) (4.4.2)\n", + "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from scikit-learn<0.22.0,>=0.20.2->snorkel==0.9.6) (1.0.1)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.7/dist-packages (from torch<2.0.0,>=1.2.0->snorkel==0.9.6) (3.7.4.3)\n", + "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas<2.0.0,>=0.25.0->snorkel==0.9.6) (2.8.1)\n", + "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas<2.0.0,>=0.25.0->snorkel==0.9.6) (2018.9)\n", + "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (4.5.0)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard<2.0.0,>=1.14.0->snorkel==0.9.6) (3.4.1)\n", + "Building wheels for collected packages: networkx\n", + " Building wheel for networkx (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for networkx: filename=networkx-2.3-py2.py3-none-any.whl size=1556427 sha256=fe9bd053c6e9c3cf9d5a0e106e6d244b52e73825d565d18c2eb34ee2663b4f55\n", + " Stored in directory: /root/.cache/pip/wheels/de/63/64/3699be2a9d0ccdb37c7f16329acf3863fd76eda58c39c737af\n", + "Successfully built networkx\n", + "\u001b[31mERROR: tensorflow 2.5.0 has requirement tensorboard~=2.5, but you'll have tensorboard 1.15.0 which is incompatible.\u001b[0m\n", + "\u001b[31mERROR: albumentations 0.1.12 has requirement imgaug<0.2.7,>=0.2.5, but you'll have imgaug 0.2.9 which is incompatible.\u001b[0m\n", + "Installing collected packages: tensorboard, munkres, networkx, scikit-learn, snorkel\n", + " Found existing installation: tensorboard 2.5.0\n", + " Uninstalling tensorboard-2.5.0:\n", + " Successfully uninstalled tensorboard-2.5.0\n", + " Found existing installation: networkx 2.5.1\n", + " Uninstalling networkx-2.5.1:\n", + " Successfully uninstalled networkx-2.5.1\n", + " Found existing installation: scikit-learn 0.22.2.post1\n", + " Uninstalling scikit-learn-0.22.2.post1:\n", + " Successfully uninstalled scikit-learn-0.22.2.post1\n", + "Successfully installed munkres-1.1.4 networkx-2.3 scikit-learn-0.21.3 snorkel-0.9.6 tensorboard-1.15.0\n", + "Collecting treedlib==0.1.3\n", + " Downloading https://files.pythonhosted.org/packages/2c/44/d0880af1f8f14e4b6c71da161648cac8ff8231965383f11b65540f751fa7/treedlib-0.1.3-py3-none-any.whl\n", + "Requirement already satisfied: lxml in /usr/local/lib/python3.7/dist-packages (from treedlib==0.1.3) (4.2.6)\n", + "Installing collected packages: treedlib\n", + "Successfully installed treedlib-0.1.3\n", + "Collecting numbskull==0.1.1\n", + " Downloading https://files.pythonhosted.org/packages/c8/56/03f98485dec32d15522a59d35d87107a46375288a7a4ee1fffde7ff8fff2/numbskull-0.1.1-py3-none-any.whl\n", + "Requirement already satisfied: future in /usr/local/lib/python3.7/dist-packages (from numbskull==0.1.1) (0.16.0)\n", + "Installing collected packages: numbskull\n", + "Successfully installed numbskull-0.1.1\n", + "Collecting tensorflow==1.15\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/92/2b/e3af15221da9ff323521565fa3324b0d7c7c5b1d7a8ca66984c8d59cb0ce/tensorflow-1.15.0-cp37-cp37m-manylinux2010_x86_64.whl (412.3MB)\n", + "\u001b[K |████████████████████████████████| 412.3MB 29kB/s \n", + "\u001b[?25hRequirement already satisfied: tensorboard<1.16.0,>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.15.0)\n", + "Requirement already satisfied: google-pasta>=0.1.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (0.2.0)\n", + "Requirement already satisfied: astor>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (0.8.1)\n", + "Requirement already satisfied: absl-py>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (0.12.0)\n", + "Requirement already satisfied: keras-preprocessing>=1.0.5 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.1.2)\n", + "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (3.3.0)\n", + "Collecting tensorflow-estimator==1.15.1\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/de/62/2ee9cd74c9fa2fa450877847ba560b260f5d0fb70ee0595203082dafcc9d/tensorflow_estimator-1.15.1-py2.py3-none-any.whl (503kB)\n", + "\u001b[K |████████████████████████████████| 512kB 42.4MB/s \n", + "\u001b[?25hRequirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.1.0)\n", + "Collecting keras-applications>=1.0.8\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/71/e3/19762fdfc62877ae9102edf6342d71b28fbfd9dea3d2f96a882ce099b03f/Keras_Applications-1.0.8-py3-none-any.whl (50kB)\n", + "\u001b[K |████████████████████████████████| 51kB 7.0MB/s \n", + "\u001b[?25hRequirement already satisfied: numpy<2.0,>=1.16.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.19.5)\n", + "Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.15.0)\n", + "Requirement already satisfied: wrapt>=1.11.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.12.1)\n", + "Collecting gast==0.2.2\n", + " Downloading https://files.pythonhosted.org/packages/4e/35/11749bf99b2d4e3cceb4d55ca22590b0d7c2c62b9de38ac4a4a7f4687421/gast-0.2.2.tar.gz\n", + "Requirement already satisfied: protobuf>=3.6.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (3.12.4)\n", + "Requirement already satisfied: grpcio>=1.8.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (1.34.1)\n", + "Requirement already satisfied: wheel>=0.26 in /usr/local/lib/python3.7/dist-packages (from tensorflow==1.15) (0.36.2)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (57.0.0)\n", + "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.3.4)\n", + "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (1.0.1)\n", + "Requirement already satisfied: h5py in /usr/local/lib/python3.7/dist-packages (from keras-applications>=1.0.8->tensorflow==1.15) (3.1.0)\n", + "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (4.5.0)\n", + "Requirement already satisfied: cached-property; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from h5py->keras-applications>=1.0.8->tensorflow==1.15) (1.5.2)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.4.1)\n", + "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard<1.16.0,>=1.15.0->tensorflow==1.15) (3.7.4.3)\n", + "Building wheels for collected packages: gast\n", + " Building wheel for gast (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for gast: filename=gast-0.2.2-cp37-none-any.whl size=7557 sha256=b9b362dc4c0d1e05be50daaf72075a04f18eb1de2cb83ad4cf5ec6942c4c099d\n", + " Stored in directory: /root/.cache/pip/wheels/5c/2e/7e/a1d4d4fcebe6c381f378ce7743a3ced3699feb89bcfbdadadd\n", + "Successfully built gast\n", + "\u001b[31mERROR: tensorflow-probability 0.12.1 has requirement gast>=0.3.2, but you'll have gast 0.2.2 which is incompatible.\u001b[0m\n", + "\u001b[31mERROR: kapre 0.3.5 has requirement tensorflow>=2.0.0, but you'll have tensorflow 1.15.0 which is incompatible.\u001b[0m\n", + "Installing collected packages: tensorflow-estimator, keras-applications, gast, tensorflow\n", + " Found existing installation: tensorflow-estimator 2.5.0\n", + " Uninstalling tensorflow-estimator-2.5.0:\n", + " Successfully uninstalled tensorflow-estimator-2.5.0\n", + " Found existing installation: gast 0.4.0\n", + " Uninstalling gast-0.4.0:\n", + " Successfully uninstalled gast-0.4.0\n", + " Found existing installation: tensorflow 2.5.0\n", + " Uninstalling tensorflow-2.5.0:\n", + " Successfully uninstalled tensorflow-2.5.0\n", + "Successfully installed gast-0.2.2 keras-applications-1.0.8 tensorflow-1.15.0 tensorflow-estimator-1.15.1\n", + "Requirement already satisfied: tensorboard==1.15 in /usr/local/lib/python3.7/dist-packages (1.15.0)\n", + "Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (0.12.0)\n", + "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (3.3.4)\n", + "Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (0.36.2)\n", + "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (57.0.0)\n", + "Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (1.15.0)\n", + "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (1.0.1)\n", + "Requirement already satisfied: protobuf>=3.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (3.12.4)\n", + "Requirement already satisfied: grpcio>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (1.34.1)\n", + "Requirement already satisfied: numpy>=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard==1.15) (1.19.5)\n", + "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard==1.15) (4.5.0)\n", + "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard==1.15) (3.7.4.3)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard==1.15) (3.4.1)\n", + "Collecting wget\n", + " Downloading https://files.pythonhosted.org/packages/47/6a/62e288da7bcda82b935ff0c6cfe542970f04e29c756b0e147251b2fb251f/wget-3.2.zip\n", + "Building wheels for collected packages: wget\n", + " Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for wget: filename=wget-3.2-cp37-none-any.whl size=9675 sha256=0ee752c74ee35d6038de394ff408eb5e7a9dfe00e1e53a8cd5940483007dc86a\n", + " Stored in directory: /root/.cache/pip/wheels/40/15/30/7d8f7cea2902b4db79e3fea550d7d7b85ecb27ef992b618f3f\n", + "Successfully built wget\n", + "Installing collected packages: wget\n", + "Successfully installed wget-3.2\n", + "Requirement already satisfied: textblob in /usr/local/lib/python3.7/dist-packages (0.15.3)\n", + "Requirement already satisfied: nltk>=3.1 in /usr/local/lib/python3.7/dist-packages (from textblob) (3.2.5)\n", + "Requirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from nltk>=3.1->textblob) (1.15.0)\n", + "Requirement already satisfied: en_core_web_sm==2.2.5 from https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-2.2.5/en_core_web_sm-2.2.5.tar.gz#egg=en_core_web_sm==2.2.5 in /usr/local/lib/python3.7/dist-packages (2.2.5)\n", + "Requirement already satisfied: spacy>=2.2.2 in /usr/local/lib/python3.7/dist-packages (from en_core_web_sm==2.2.5) (2.2.4)\n", + "Requirement already satisfied: wasabi<1.1.0,>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (0.8.2)\n", + "Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (57.0.0)\n", + "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (2.23.0)\n", + "Requirement already satisfied: blis<0.5.0,>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (0.4.1)\n", + "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (3.0.5)\n", + "Requirement already satisfied: plac<1.2.0,>=0.9.6 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (1.1.3)\n", + "Requirement already satisfied: numpy>=1.15.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (1.19.5)\n", + "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (1.0.5)\n", + "Requirement already satisfied: srsly<1.1.0,>=1.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (1.0.5)\n", + "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (2.0.5)\n", + "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (4.41.1)\n", + "Requirement already satisfied: thinc==7.4.0 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (7.4.0)\n", + "Requirement already satisfied: catalogue<1.1.0,>=0.0.7 in /usr/local/lib/python3.7/dist-packages (from spacy>=2.2.2->en_core_web_sm==2.2.5) (1.0.0)\n", + "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=2.2.2->en_core_web_sm==2.2.5) (3.0.4)\n", + "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=2.2.2->en_core_web_sm==2.2.5) (2.10)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=2.2.2->en_core_web_sm==2.2.5) (2021.5.30)\n", + "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3.0.0,>=2.13.0->spacy>=2.2.2->en_core_web_sm==2.2.5) (1.24.3)\n", + "Requirement already satisfied: importlib-metadata>=0.20; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from catalogue<1.1.0,>=0.0.7->spacy>=2.2.2->en_core_web_sm==2.2.5) (4.5.0)\n", + "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=0.20; python_version < \"3.8\"->catalogue<1.1.0,>=0.0.7->spacy>=2.2.2->en_core_web_sm==2.2.5) (3.4.1)\n", + "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=0.20; python_version < \"3.8\"->catalogue<1.1.0,>=0.0.7->spacy>=2.2.2->en_core_web_sm==2.2.5) (3.7.4.3)\n", + "\u001b[38;5;2m✔ Download and installation successful\u001b[0m\n", + "You can now load the model via spacy.load('en_core_web_sm')\n" ] } ], @@ -164,6 +203,8 @@ "!pip install numbskull==0.1.1\n", "!pip install tensorflow==1.15\n", "!pip install tensorboard==1.15\n", + "!pip install wget\n", + "!pip install textblob\n", "!python -m spacy download en_core_web_sm" ] }, @@ -174,7 +215,8 @@ "ExecuteTime": { "end_time": "2021-04-03T11:08:02.765409Z", "start_time": "2021-04-03T11:08:02.750395Z" - } + }, + "id": "1_TfLGPSr3OQ" }, "outputs": [], "source": [ @@ -185,7 +227,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "fYsYe4tOomEM" }, "source": [ @@ -200,28 +241,28 @@ "ExecuteTime": { "end_time": "2021-04-03T11:08:04.193561Z", "start_time": "2021-04-03T11:08:02.766409Z" - } + }, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "1hO0ncklr3OR", + "outputId": "d92aa059-86fb-4395-cbaf-2fc9198f2825" }, "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "100% [............................................................................] 163567 / 163567" - ] - }, { "data": { "text/plain": [ - "['Youtube01-Psy.csv',\n", + "['Youtube05-Shakira.csv',\n", " 'Youtube02-KatyPerry.csv',\n", " 'Youtube03-LMFAO.csv',\n", - " 'Youtube04-Eminem.csv',\n", - " 'Youtube05-Shakira.csv']" + " 'Youtube01-Psy.csv',\n", + " 'Youtube04-Eminem.csv']" ] }, "execution_count": 3, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -251,7 +292,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "H2msvroyoZ5W" }, "source": [ @@ -267,19 +307,23 @@ "start_time": "2021-04-03T11:08:04.194562Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 139 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "F2MGdPXm7IvY", - "outputId": "2e2079af-2b09-4006-cb64-7e4a374071c9" + "outputId": "e19dd48c-20ee-4f49-92d5-b3e123feb1b9" }, "outputs": [ { - "name": "stderr", + "name": "stdout", "output_type": "stream", "text": [ - "Cloning into 'snorkel-tutorials'...\n" + "Cloning into 'snorkel-tutorials'...\n", + "remote: Enumerating objects: 1124, done.\u001b[K\n", + "remote: Counting objects: 100% (65/65), done.\u001b[K\n", + "remote: Compressing objects: 100% (56/56), done.\u001b[K\n", + "remote: Total 1124 (delta 28), reused 15 (delta 8), pack-reused 1059\u001b[K\n", + "Receiving objects: 100% (1124/1124), 3.53 MiB | 19.66 MiB/s, done.\n", + "Resolving deltas: 100% (743/743), done.\n" ] } ], @@ -302,7 +346,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "XM6JWmh6oxtv" }, "source": [ @@ -317,8 +360,6 @@ "end_time": "2021-04-03T11:08:10.334905Z", "start_time": "2021-04-03T11:08:06.478745Z" }, - "colab": {}, - "colab_type": "code", "id": "h-vgmzc7B0PM", "scrolled": true }, @@ -365,7 +406,8 @@ "ExecuteTime": { "end_time": "2021-04-03T11:08:10.350918Z", "start_time": "2021-04-03T11:08:10.335905Z" - } + }, + "id": "0Lp8IEfZr3OT" }, "outputs": [], "source": [ @@ -412,11 +454,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 448 + "height": 407 }, - "colab_type": "code", "id": "PQ_a_pkV3tdR", - "outputId": "037e36ad-5c7e-4ea6-9daf-2ee959847dd7", + "outputId": "01776a69-84fd-407d-c4f2-4c804321329e", "scrolled": false }, "outputs": [ @@ -501,22 +542,19 @@ "" ], "text/plain": [ - " author date \\\n", - "0 Alessandro leite 2014-11-05T22:21:36 \n", - "1 Salim Tayara 2014-11-02T14:33:30 \n", - "2 Phuc Ly 2014-01-20T15:27:47 \n", - "3 DropShotSk8r 2014-01-19T04:27:18 \n", - "4 css403 2014-11-07T14:25:48 \n", + " author date ... label video\n", + "0 Alessandro leite 2014-11-05T22:21:36 ... -1.0 1\n", + "1 Salim Tayara 2014-11-02T14:33:30 ... -1.0 1\n", + "2 Phuc Ly 2014-01-20T15:27:47 ... -1.0 1\n", + "3 DropShotSk8r 2014-01-19T04:27:18 ... -1.0 1\n", + "4 css403 2014-11-07T14:25:48 ... -1.0 1\n", "\n", - " text label video \n", - "0 pls http://www10.vakinha.com.br/VaquinhaE.aspx... -1.0 1 \n", - "1 if your like drones, plz subscribe to Kamal Ta... -1.0 1 \n", - "2 go here to check the views :3 -1.0 1 \n", - "3 Came here to check the views, goodbye. -1.0 1 \n", - "4 i am 2,126,492,636 viewer :D -1.0 1 " + "[5 rows x 5 columns]" ] }, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "display_data" }, { @@ -600,23 +638,20 @@ "" ], "text/plain": [ - " author date \\\n", - "27 ‫حلم الشباب‬‎ 2015-05-25T23:42:49.533000 \n", - "194 MOHAMED THASLEEM 2015-05-24T07:03:59.488000 \n", - "277 AlabaGames 2015-05-22T00:31:43.922000 \n", - "132 Manish Ray 2015-05-23T08:55:07.512000 \n", - "163 Sudheer Yadav 2015-05-28T10:28:25.133000 \n", + " author date ... label video\n", + "27 ‫حلم الشباب‬‎ 2015-05-25T23:42:49.533000 ... 1 5\n", + "194 MOHAMED THASLEEM 2015-05-24T07:03:59.488000 ... 0 5\n", + "277 AlabaGames 2015-05-22T00:31:43.922000 ... 1 5\n", + "132 Manish Ray 2015-05-23T08:55:07.512000 ... 0 5\n", + "163 Sudheer Yadav 2015-05-28T10:28:25.133000 ... 1 5\n", "\n", - " text label video \n", - "27 Check out this video on YouTube: 1 5 \n", - "194 super music 0 5 \n", - "277 Subscribe my channel  I RECORDING FIFA 15 GOAL... 1 5 \n", - "132 This song is so beauty 0 5 \n", - "163 SEE SOME MORE SONG OPEN GOOGLE AND TYPE Shakir... 1 5 " + "[5 rows x 5 columns]" ] }, "execution_count": 7, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -637,34 +672,33 @@ "start_time": "2021-04-03T11:08:10.448007Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "sYk70EPO4sk3", - "outputId": "db2db996-7faa-453d-c3d7-0e1049dc8d81" + "outputId": "cedead41-f044-48e7-fce0-9a3e5c80e645" }, "outputs": [ { "data": { "text/plain": [ - "array([1, 0, 1, 0, 1], dtype=int64)" + "array([1, 0, 1, 0, 1, 0, 1, 0, 1, 1])" ] }, "execution_count": 8, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], "source": [ "Y_test = df_test.label.values\n", - "Y_test[:5]" + "Y_test[:10]" ] }, { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "YSxLJ9P2ptsG" }, "source": [ @@ -684,8 +718,6 @@ "end_time": "2021-04-03T11:08:10.478036Z", "start_time": "2021-04-03T11:08:10.464021Z" }, - "colab": {}, - "colab_type": "code", "id": "BUPjY_nKbJEM" }, "outputs": [], @@ -698,7 +730,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "AA94SzMiqJQq" }, "source": [ @@ -716,11 +747,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 677 + "height": 639 }, - "colab_type": "code", "id": "fz2VcSoNbMi2", - "outputId": "67aa06eb-5117-485d-a042-f6086c7983ff" + "outputId": "fafc6a04-e14b-4f19-b8ff-937272c5e6d6" }, "outputs": [ { @@ -875,53 +905,35 @@ "" ], "text/plain": [ - " author \\\n", - "240 Lucas Trigo \n", - "211 Blaze Rod \n", - "228 MasterRobotTV \n", - "207 Franklin Music \n", - "153 lebanonwarior1 \n", - "8 yenis maría Rodríguez \n", - "62 RapStarz Coleman \n", - "54 Jd Hurst \n", - "353 jefflynnejp \n", - "406 eliška žáková \n", - "375 Chris Bieber \n", - "270 Angela Alor \n", - "44 BlueYetiPlayz -Call Of Duty and More \n", - "295 the34104 \n", - "223 Truc Ng \n", - "144 Nina Mackie \n", - "340 DanteBTV \n", - "19 Paul Garza \n", - "185 Bo Lanciné MAGASSOUBA \n", - "73 MrValentinique \n", + " author ... video\n", + "240 Lucas Trigo ... 1\n", + "211 Blaze Rod ... 3\n", + "228 MasterRobotTV ... 1\n", + "207 Franklin Music ... 3\n", + "153 lebanonwarior1 ... 1\n", + "8 yenis maría Rodríguez ... 3\n", + "62 RapStarz Coleman ... 4\n", + "54 Jd Hurst ... 3\n", + "353 jefflynnejp ... 3\n", + "406 eliška žáková ... 3\n", + "375 Chris Bieber ... 4\n", + "270 Angela Alor ... 3\n", + "44 BlueYetiPlayz -Call Of Duty and More ... 1\n", + "295 the34104 ... 4\n", + "223 Truc Ng ... 2\n", + "144 Nina Mackie ... 3\n", + "340 DanteBTV ... 4\n", + "19 Paul Garza ... 3\n", + "185 Bo Lanciné MAGASSOUBA ... 4\n", + "73 MrValentinique ... 1\n", "\n", - " text video \n", - "240 WHATS UP EVERYONE!? :-) I Trying To Showcase M... 1 \n", - "211 when i see this back in 2015 i ask myself how ... 3 \n", - "228 http://www.twitch.tv/zxlightsoutxz 1 \n", - "207 Very Nice ! 3 \n", - "153 Song name?? 1 \n", - "8 2015 LIKEEE 3 \n", - "62 Subscribe To Mê Please Guys 4 \n", - "54 Check out this video on YouTube: 3 \n", - "353 Check out this video on YouTube:  3 \n", - "406 CUTE  :) 3 \n", - "375 Love the way you lie II is nicer in my opinion... 4 \n", - "270 HOW DO YOU PUT A PICTURE FOR YOUR IMAGE THINGI... 3 \n", - "44 subscribe to me for call of duty vids and give... 1 \n", - "295 check out eminem latest track survival if u didnt 4 \n", - "223 https://www.facebook.com/myfunnyriddles 2 \n", - "144 Take a look at this video on YouTub
You 3 \n", - "340 Check Out The New Hot Video By Dante B Called ... 4 \n", - "19 Check out this video on YouTube: 3 \n", - "185 WE GO FOR 1,000,000,000 FOR EMINEM 4 \n", - "73 https://www.facebook.com/eeccon/posts/73394924... 1 " + "[20 rows x 3 columns]" ] }, "execution_count": 10, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -932,7 +944,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "8Pin_a-epBXr" }, "source": [ @@ -947,8 +958,6 @@ "end_time": "2021-04-03T11:08:10.510064Z", "start_time": "2021-04-03T11:08:10.496052Z" }, - "colab": {}, - "colab_type": "code", "id": "mpSoy45Mblnr" }, "outputs": [], @@ -962,7 +971,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "NcVpGTOpqbSr" }, "source": [ @@ -978,8 +986,6 @@ "end_time": "2021-04-03T11:08:10.526079Z", "start_time": "2021-04-03T11:08:10.511065Z" }, - "colab": {}, - "colab_type": "code", "id": "OI9-aAYAbs1e" }, "outputs": [], @@ -994,17 +1000,16 @@ "\n", "@labeling_function()\n", "def my_channel(x):\n", - " return SPAM if \"my channel\" in x.text.lower() else ABSTAIN\n", + " return SPAM if \"my channel\" in x.text.lower() else ABSTAIN\n", "\n", "@labeling_function()\n", "def if_subscribe(x):\n", - " return SPAM if \"subscribe\" in x.text.lower() else ABSTAIN" + " return SPAM if \"subscribe\" in x.text.lower() else ABSTAIN" ] }, { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "VmBAWflGqzCL" }, "source": [ @@ -1022,19 +1027,17 @@ "start_time": "2021-04-03T11:08:10.527080Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "Ab5nnlrzcUBY", - "outputId": "6352eddb-c673-4fef-e100-b2d74c984710" + "outputId": "955fade7-040c-4e4e-8be1-791e89dd8e1f" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|███████████████████████████████████████████████████████████████████████████| 1586/1586 [00:00<00:00, 23649.62it/s]\n" + "100%|██████████| 1586/1586 [00:00<00:00, 13520.09it/s]\n" ] } ], @@ -1054,12 +1057,10 @@ "start_time": "2021-04-03T11:08:10.607070Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 139 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "iEQOljcHcZh1", - "outputId": "03b69925-a749-4da0-b43b-093dd99a5dcc" + "outputId": "d4415c36-a388-4d5b-b023-ffd4c2a64074" }, "outputs": [ { @@ -1075,7 +1076,9 @@ ] }, "execution_count": 14, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1086,7 +1089,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "l6vJmvsgrl9O" }, "source": [ @@ -1102,12 +1104,10 @@ "start_time": "2021-04-03T11:08:10.622084Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 104 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "LZS3HRs1c7BB", - "outputId": "5e14598b-c60d-40a5-960e-5cbac8c28e6f" + "outputId": "8fed2489-93ff-42bc-fdb7-0903b09e5054" }, "outputs": [ { @@ -1134,7 +1134,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "I_Lflxdir08t" }, "source": [ @@ -1156,11 +1155,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 206 + "height": 195 }, - "colab_type": "code", "id": "Hb63fpwQdqin", - "outputId": "3687be18-3e39-429d-a179-4dbacf8de494" + "outputId": "eb38910a-f638-4cb3-e9f7-6974d475fe27" }, "outputs": [ { @@ -1246,7 +1244,9 @@ ] }, "execution_count": 16, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1257,7 +1257,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "lMAK17fqtOAK" }, "source": [ @@ -1274,11 +1273,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 363 + "height": 343 }, - "colab_type": "code", "id": "QHSdjvyVd2QB", - "outputId": "8024e6a5-f1d9-49bd-c063-ea5bd52f48ee" + "outputId": "ad70a3fa-f30b-40f1-a880-dd0872027b95" }, "outputs": [ { @@ -1395,33 +1393,25 @@ "" ], "text/plain": [ - " author date \\\n", - "34 TA Stealth 2015-03-11T01:25:46.234000 \n", - "288 ItsJoey Dash 2014-07-22T10:02:25.925000 \n", - "36 Victor Gamer 2015-04-13T02:00:20.152000 \n", - "263 Backup Plus 2014-11-03T17:39:07 \n", - "386 ItsJoey Dash 2014-07-22T10:04:05.755000 \n", - "404 M.E.S NaN \n", - "341 superfacoo NaN \n", - "229 Terry-Lee Mackenney NaN \n", - "157 TopMusicWorld HD 2014-10-19T23:27:50 \n", - "48 Kiddy Kidso 2014-01-19T16:49:52 \n", + " author date ... label video\n", + "34 TA Stealth 2015-03-11T01:25:46.234000 ... -1.0 3\n", + "288 ItsJoey Dash 2014-07-22T10:02:25.925000 ... -1.0 3\n", + "36 Victor Gamer 2015-04-13T02:00:20.152000 ... -1.0 3\n", + "263 Backup Plus 2014-11-03T17:39:07 ... -1.0 1\n", + "386 ItsJoey Dash 2014-07-22T10:04:05.755000 ... -1.0 3\n", + "404 M.E.S NaN ... -1.0 4\n", + "341 superfacoo NaN ... -1.0 4\n", + "229 Terry-Lee Mackenney NaN ... -1.0 4\n", + "157 TopMusicWorld HD 2014-10-19T23:27:50 ... -1.0 2\n", + "48 Kiddy Kidso 2014-01-19T16:49:52 ... -1.0 1\n", "\n", - " text label video \n", - "34 Cool Video LMFAOVEVO! You should check out my ... -1.0 3 \n", - "288 EVERYONE PLEASE GO SUBSCRIBE TO MY CHANNEL OR ... -1.0 3 \n", - "36 View 851.247.920

 Best youtube Vide... -1.0 3 \n", - "263 Suscribe My Channel Please XD lol -1.0 1 \n", - "386 EVERYONE PLEASE SUBSCRIBE TO MY CHANNEL OR CAN... -1.0 3 \n", - "404 hey its M.E.S here I'm a young up and comi... -1.0 4 \n", - "341 Hey? Everyone Please take a moment to read thi... -1.0 4 \n", - "229 Hi Guys im an Upcoming Rapper if you could che... -1.0 4 \n", - "157 Please Subscribe In My Channel → -1.0 2 \n", - "48 Check my channel please! And listen to the bes... -1.0 1 " + "[10 rows x 5 columns]" ] }, "execution_count": 17, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1434,7 +1424,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "brmOFPoMtefG" }, "source": [ @@ -1451,11 +1440,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 363 + "height": 343 }, - "colab_type": "code", "id": "SCup4XPReLeE", - "outputId": "ebce9e4c-011b-4f81-8e57-78c257ddd4a1" + "outputId": "252e4980-07a7-4d68-d700-2e91920949f0" }, "outputs": [ { @@ -1572,33 +1560,25 @@ "" ], "text/plain": [ - " author date \\\n", - "230 LBEProductions 2014-11-12T01:40:22 \n", - "287 DERRICK HANFORD 2014-12-05T22:52:29.316000 \n", - "113 Carlos Thegamer 2013-12-01T01:20:21 \n", - "301 Ractive NaN \n", - "246 Patrik Gybka 2015-05-05T09:32:04.687000 \n", - "8 Youyou A. 2014-10-21T15:20:49 \n", - "333 FreexGaming 2014-10-18T08:12:26 \n", - "161 MarianMusicChannel 2014-08-24T03:57:52 \n", - "171 MR magic man 2014-09-25T10:42:47 \n", - "10 Dany PK NaN \n", + " author date ... label video\n", + "230 LBEProductions 2014-11-12T01:40:22 ... -1.0 1\n", + "287 DERRICK HANFORD 2014-12-05T22:52:29.316000 ... -1.0 3\n", + "113 Carlos Thegamer 2013-12-01T01:20:21 ... -1.0 1\n", + "301 Ractive NaN ... -1.0 4\n", + "246 Patrik Gybka 2015-05-05T09:32:04.687000 ... -1.0 3\n", + "8 Youyou A. 2014-10-21T15:20:49 ... -1.0 2\n", + "333 FreexGaming 2014-10-18T08:12:26 ... -1.0 2\n", + "161 MarianMusicChannel 2014-08-24T03:57:52 ... -1.0 2\n", + "171 MR magic man 2014-09-25T10:42:47 ... -1.0 2\n", + "10 Dany PK NaN ... -1.0 4\n", "\n", - " text label video \n", - "230 Hey guys can you check my channel out plz. I d... -1.0 1 \n", - "287 White people are going extinct for more inform... -1.0 3 \n", - "113 subscribe to my channel people :D -1.0 1 \n", - "301 i been working so hard for the past 60 days to... -1.0 4 \n", - "246 SUBSCRIBE MY CHANNEL PLEASE LOL PRO PLAYS) -1.0 3 \n", - "8 I make guitar covers, please have a look at my... -1.0 2 \n", - "333 want to win borderlands the pre-sequel? check ... -1.0 2 \n", - "161 Hello! I'm Marian, I'm a singer from Venezuela... -1.0 2 \n", - "171 Please look at my channel -1.0 2 \n", - "10 SUBSCRIBE TO MY CHANNEL X PLEASE!. SPARE -1.0 4 " + "[10 rows x 5 columns]" ] }, "execution_count": 18, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1613,7 +1593,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "oHmTYt8btmcb" }, "source": [ @@ -1630,8 +1609,6 @@ "end_time": "2021-04-03T11:08:10.701156Z", "start_time": "2021-04-03T11:08:10.686143Z" }, - "colab": {}, - "colab_type": "code", "id": "DumNxb_PiEeN" }, "outputs": [], @@ -1651,19 +1628,17 @@ "start_time": "2021-04-03T11:08:10.702157Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "fkgLHcPgkkQV", - "outputId": "95e329d7-f31b-47fc-9052-daf1b9b11ebe" + "outputId": "23fb4f98-84b3-4798-9b39-eb7dd65a7c9f" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|███████████████████████████████████████████████████████████████████████████| 1586/1586 [00:00<00:00, 35212.86it/s]\n" + "100%|██████████| 1586/1586 [00:00<00:00, 22789.90it/s]\n" ] } ], @@ -1684,11 +1659,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 143 + "height": 136 }, - "colab_type": "code", "id": "854a-lHSkpB3", - "outputId": "a7b30b81-4880-40cd-d520-2f55e24bb6fd" + "outputId": "f1a69983-1858-447f-c1e6-0d57e99b81ec" }, "outputs": [ { @@ -1756,7 +1730,9 @@ ] }, "execution_count": 21, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1774,11 +1750,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 363 + "height": 343 }, - "colab_type": "code", "id": "HaQZ-7PolblW", - "outputId": "a06d2efa-ed06-4f37-ddea-9d6334f916af" + "outputId": "92212dd8-bc90-4495-a325-393e56f5997e" }, "outputs": [ { @@ -1895,33 +1870,25 @@ "" ], "text/plain": [ - " author date \\\n", - "112 ArioseRose 2014-11-13T15:20:31 \n", - "273 Artady 2014-08-11T16:27:55 \n", - "190 Warrdrew 2014-11-07T07:46:57 \n", - "146 Bob Kanowski 2013-11-28T12:33:27 \n", - "139 MFkin PRXPHETZ 2014-01-20T09:08:39 \n", - "191 RezAIIDay 2014-11-05T22:50:58 \n", - "16 zhichao wang 2013-11-29T02:13:56 \n", - "162 Owen Lai 2013-12-01T04:51:52 \n", - "239 Cony 2013-11-28T16:01:47 \n", - "322 Minecraft-Viasat 2014-11-03T14:38:53 \n", + " author date ... label video\n", + "112 ArioseRose 2014-11-13T15:20:31 ... -1.0 1\n", + "273 Artady 2014-08-11T16:27:55 ... -1.0 2\n", + "190 Warrdrew 2014-11-07T07:46:57 ... -1.0 1\n", + "146 Bob Kanowski 2013-11-28T12:33:27 ... -1.0 1\n", + "139 MFkin PRXPHETZ 2014-01-20T09:08:39 ... -1.0 1\n", + "191 RezAIIDay 2014-11-05T22:50:58 ... -1.0 2\n", + "16 zhichao wang 2013-11-29T02:13:56 ... -1.0 1\n", + "162 Owen Lai 2013-12-01T04:51:52 ... -1.0 1\n", + "239 Cony 2013-11-28T16:01:47 ... -1.0 1\n", + "322 Minecraft-Viasat 2014-11-03T14:38:53 ... -1.0 1\n", "\n", - " text label video \n", - "112 Don't mind me, I'm just checking what the view... -1.0 1 \n", - "273 https://soundcloud.com/artady please check my ... -1.0 2 \n", - "190 I'm here to check the views.. holy shit -1.0 1 \n", - "146 i turned it on mute as soon is i came on i jus... -1.0 1 \n", - "139 if you like raw talent, raw lyrics, straight r... -1.0 1 \n", - "191 Such a good song ans Katy sounds great over th... -1.0 2 \n", - "16 i think about 100 millions of the views come f... -1.0 1 \n", - "162 just checking the views -1.0 1 \n", - "239 You should check my channel for Funny VIDEOS!! -1.0 1 \n", - "322 Check my channel -1.0 1 " + "[10 rows x 5 columns]" ] }, "execution_count": 22, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -1933,7 +1900,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "646laecIt2y4" }, "source": [ @@ -1948,8 +1914,6 @@ "end_time": "2021-04-03T11:08:10.812635Z", "start_time": "2021-04-03T11:08:10.798620Z" }, - "colab": {}, - "colab_type": "code", "id": "oBMqQuBUmRz1" }, "outputs": [], @@ -1970,8 +1934,6 @@ "end_time": "2021-04-03T11:08:10.828649Z", "start_time": "2021-04-03T11:08:10.814636Z" }, - "colab": {}, - "colab_type": "code", "id": "u97Ql5_W6MNf" }, "outputs": [], @@ -1994,19 +1956,17 @@ "start_time": "2021-04-03T11:08:10.829650Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "2pJl0yod-qMe", - "outputId": "2b45ce28-6592-4472-e559-141454da5f2b" + "outputId": "b927d1cb-a39b-4119-c492-53fabc9e212a" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|████████████████████████████████████████████████████████████████████████████| 1586/1586 [00:01<00:00, 1445.44it/s]\n" + "100%|██████████| 1586/1586 [00:01<00:00, 1088.23it/s]\n" ] } ], @@ -2027,11 +1987,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 112 + "height": 106 }, - "colab_type": "code", "id": "q5NVqhPr--EO", - "outputId": "f1e6133e-25e4-4713-a9d5-9e95829669ff" + "outputId": "246bdc68-3388-4842-967a-860bd55bee33" }, "outputs": [ { @@ -2090,7 +2049,9 @@ ] }, "execution_count": 26, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -2101,7 +2062,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "UZxFsE-vH47d" }, "source": [ @@ -2113,7 +2073,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "QuOJYTmNgjK5" }, "source": [ @@ -2128,13 +2087,10 @@ "end_time": "2021-04-03T11:08:11.976404Z", "start_time": "2021-04-03T11:08:11.961384Z" }, - "colab": {}, - "colab_type": "code", "id": "MZNRemLj_Bx2" }, "outputs": [], "source": [ - "\n", "def keyword_lookup(x, keywords, label):\n", " if any(word in x.text.lower() for word in keywords):\n", " return label\n", @@ -2168,7 +2124,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "ZxDDetHLhp59" }, "source": [ @@ -2187,8 +2142,6 @@ "end_time": "2021-04-03T11:08:11.992370Z", "start_time": "2021-04-03T11:08:11.977405Z" }, - "colab": {}, - "colab_type": "code", "id": "ZeNvjhdkhUSK" }, "outputs": [], @@ -2202,7 +2155,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "I3GOjwZtiwfw" }, "source": [ @@ -2217,8 +2169,6 @@ "end_time": "2021-04-03T11:08:17.522364Z", "start_time": "2021-04-03T11:08:11.993372Z" }, - "colab": {}, - "colab_type": "code", "id": "TZ2p4AW1iegt" }, "outputs": [], @@ -2244,8 +2194,6 @@ "end_time": "2021-04-03T11:08:22.239568Z", "start_time": "2021-04-03T11:08:17.523293Z" }, - "colab": {}, - "colab_type": "code", "id": "Ya5diNfSlRA1" }, "outputs": [], @@ -2264,7 +2212,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "yOL67OFB2N5b" }, "source": [ @@ -2281,8 +2228,6 @@ "end_time": "2021-04-03T11:08:22.255584Z", "start_time": "2021-04-03T11:08:22.240569Z" }, - "colab": {}, - "colab_type": "code", "id": "HOFzxDkSlpiL" }, "outputs": [], @@ -2310,20 +2255,18 @@ "start_time": "2021-04-03T11:08:22.256584Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 52 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "W_y7ZTD43Ttp", - "outputId": "dd9ebd36-1528-49a6-bd23-0c7989d0d451" + "outputId": "8078dab7-62b8-4f60-ca71-de098f47def3" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "100%|█████████████████████████████████████████████████████████████████████████████| 1586/1586 [00:07<00:00, 198.89it/s]\n", - "100%|███████████████████████████████████████████████████████████████████████████████| 250/250 [00:01<00:00, 157.09it/s]\n" + "100%|██████████| 1586/1586 [00:17<00:00, 91.32it/s]\n", + "100%|██████████| 250/250 [00:03<00:00, 78.62it/s]\n" ] } ], @@ -2343,11 +2286,10 @@ }, "colab": { "base_uri": "https://localhost:8080/", - "height": 363 + "height": 343 }, - "colab_type": "code", "id": "FXEDv6Nk3a9r", - "outputId": "9a57832c-bab1-4ab0-a468-7548cacf1c70" + "outputId": "46d590c2-49df-4e43-c0c2-37e4c950bc2c" }, "outputs": [ { @@ -2384,7 +2326,7 @@ " 0\n", " [1]\n", " 0.198613\n", - " 0.185372\n", + " 0.186003\n", " 0.110340\n", " \n", " \n", @@ -2392,16 +2334,16 @@ " 1\n", " [1]\n", " 0.127364\n", - " 0.107188\n", - " 0.067465\n", + " 0.107818\n", + " 0.068096\n", " \n", " \n", " keyword_http\n", " 2\n", " [1]\n", " 0.119168\n", - " 0.100252\n", - " 0.081337\n", + " 0.102144\n", + " 0.083228\n", " \n", " \n", " keyword_please\n", @@ -2409,14 +2351,14 @@ " [1]\n", " 0.112232\n", " 0.109710\n", - " 0.058008\n", + " 0.057377\n", " \n", " \n", " keyword_song\n", " 4\n", " [0]\n", " 0.141866\n", - " 0.110340\n", + " 0.111602\n", " 0.043506\n", " \n", " \n", @@ -2424,31 +2366,31 @@ " 5\n", " [1]\n", " 0.233922\n", - " 0.129887\n", - " 0.084489\n", + " 0.133039\n", + " 0.086381\n", " \n", " \n", " short_comment\n", " 6\n", " [0]\n", " 0.225725\n", - " 0.142497\n", + " 0.144388\n", " 0.074401\n", " \n", " \n", " has_person_nlp\n", " 7\n", " [0]\n", - " 0.062421\n", - " 0.046658\n", - " 0.024590\n", + " 0.082598\n", + " 0.060530\n", + " 0.025221\n", " \n", " \n", " textblob_polarity\n", " 8\n", " [0]\n", " 0.035309\n", - " 0.031526\n", + " 0.032156\n", " 0.005044\n", " \n", " \n", @@ -2456,7 +2398,7 @@ " 9\n", " [0]\n", " 0.357503\n", - " 0.254729\n", + " 0.261665\n", " 0.160151\n", " \n", " \n", @@ -2465,20 +2407,22 @@ ], "text/plain": [ " j Polarity Coverage Overlaps Conflicts\n", - "keyword_my 0 [1] 0.198613 0.185372 0.110340\n", - "keyword_subscribe 1 [1] 0.127364 0.107188 0.067465\n", - "keyword_http 2 [1] 0.119168 0.100252 0.081337\n", - "keyword_please 3 [1] 0.112232 0.109710 0.058008\n", - "keyword_song 4 [0] 0.141866 0.110340 0.043506\n", - "regex_check_out 5 [1] 0.233922 0.129887 0.084489\n", - "short_comment 6 [0] 0.225725 0.142497 0.074401\n", - "has_person_nlp 7 [0] 0.062421 0.046658 0.024590\n", - "textblob_polarity 8 [0] 0.035309 0.031526 0.005044\n", - "textblob_subjectivity 9 [0] 0.357503 0.254729 0.160151" + "keyword_my 0 [1] 0.198613 0.186003 0.110340\n", + "keyword_subscribe 1 [1] 0.127364 0.107818 0.068096\n", + "keyword_http 2 [1] 0.119168 0.102144 0.083228\n", + "keyword_please 3 [1] 0.112232 0.109710 0.057377\n", + "keyword_song 4 [0] 0.141866 0.111602 0.043506\n", + "regex_check_out 5 [1] 0.233922 0.133039 0.086381\n", + "short_comment 6 [0] 0.225725 0.144388 0.074401\n", + "has_person_nlp 7 [0] 0.082598 0.060530 0.025221\n", + "textblob_polarity 8 [0] 0.035309 0.032156 0.005044\n", + "textblob_subjectivity 9 [0] 0.357503 0.261665 0.160151" ] }, "execution_count": 33, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -2489,7 +2433,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "fZ1F_FeH3s2-" }, "source": [ @@ -2508,27 +2451,25 @@ "base_uri": "https://localhost:8080/", "height": 281 }, - "colab_type": "code", "id": "Cer6qKcD3m_I", - "outputId": "80c22a03-4e9b-4a8b-be58-7f5eacb26c7e" + "outputId": "d1179a55-2a23-41d9-a737-dca1c5bad3ac" }, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { - "needs_background": "light" + "needs_background": "light", + "tags": [] }, "output_type": "display_data" } ], "source": [ - "\n", - "\n", "def plot_label_frequency(L):\n", " plt.hist((L != ABSTAIN).sum(axis=1), density=True, bins=range(L.shape[1]))\n", " plt.xlabel(\"Number of labels\")\n", @@ -2542,7 +2483,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "lNacdVnl4-ys" }, "source": [ @@ -2557,8 +2497,6 @@ "end_time": "2021-04-03T11:08:31.987553Z", "start_time": "2021-04-03T11:08:31.956662Z" }, - "colab": {}, - "colab_type": "code", "id": "Z-2jteSi3saV" }, "outputs": [], @@ -2576,12 +2514,10 @@ "start_time": "2021-04-03T11:08:31.988554Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "QFjnaR6Q3-Qh", - "outputId": "7da244c8-b946-400e-9685-734678cb4fed" + "outputId": "2db45f68-bfc1-45f5-d113-7ff1d9670553" }, "outputs": [ { @@ -2591,7 +2527,9 @@ ] }, "execution_count": 36, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -2602,7 +2540,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "bFwzHcVQ6MiI" }, "source": [ @@ -2617,8 +2554,6 @@ "end_time": "2021-04-03T11:08:32.305858Z", "start_time": "2021-04-03T11:08:32.004576Z" }, - "colab": {}, - "colab_type": "code", "id": "9M352m7Z5jQM" }, "outputs": [], @@ -2636,12 +2571,10 @@ "start_time": "2021-04-03T11:08:32.306859Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 52 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "wjdlmw9r6oDh", - "outputId": "ffc1753a-3e02-453a-81fe-13f4d78c199f" + "outputId": "2355c39b-af63-41b4-d41e-8252eb2b8094" }, "outputs": [ { @@ -2649,7 +2582,7 @@ "output_type": "stream", "text": [ "Majority Vote Accuracy: 84.0%\n", - "Label Model Accuracy: 86.0%\n" + "Label Model Accuracy: 86.4%\n" ] } ], @@ -2664,7 +2597,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "v5Lcyg-Q622K" }, "source": [ @@ -2683,20 +2615,20 @@ "base_uri": "https://localhost:8080/", "height": 279 }, - "colab_type": "code", "id": "nFr84u3m6qt_", - "outputId": "eb692384-d284-4598-97db-03ed610cf402" + "outputId": "e76960e4-0638-4e52-b7dd-ebb34e4aee50" }, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { - "needs_background": "light" + "needs_background": "light", + "tags": [] }, "output_type": "display_data" } @@ -2715,7 +2647,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "CO3RyIU77LYn" }, "source": [ @@ -2730,8 +2661,6 @@ "end_time": "2021-04-03T11:08:32.433862Z", "start_time": "2021-04-03T11:08:32.418849Z" }, - "colab": {}, - "colab_type": "code", "id": "hm2Uwog27Dbf" }, "outputs": [], @@ -2744,7 +2673,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "F7b3d4pz8Zcq" }, "source": [ @@ -2761,8 +2689,6 @@ "end_time": "2021-04-03T11:08:32.610022Z", "start_time": "2021-04-03T11:08:32.434863Z" }, - "colab": {}, - "colab_type": "code", "id": "9Rz10tgs7V54" }, "outputs": [], @@ -2780,8 +2706,6 @@ "end_time": "2021-04-03T11:08:32.625459Z", "start_time": "2021-04-03T11:08:32.611023Z" }, - "colab": {}, - "colab_type": "code", "id": "m07Vm3QS9FKz" }, "outputs": [], @@ -2798,12 +2722,10 @@ "start_time": "2021-04-03T11:08:32.626460Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 104 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "aHmJLIf69HR6", - "outputId": "8ee92b59-4415-49ff-d847-cea3e17bc258" + "outputId": "53ff1b0d-ea89-493b-c23b-fb6db18502be" }, "outputs": [ { @@ -2817,7 +2739,9 @@ ] }, "execution_count": 43, - "metadata": {}, + "metadata": { + "tags": [] + }, "output_type": "execute_result" } ], @@ -2835,19 +2759,17 @@ "start_time": "2021-04-03T11:08:32.802621Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 34 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "aKtmNBiw9KMa", - "outputId": "d9d78ead-86a3-4b12-d578-54bd1488cf38" + "outputId": "8a2f9174-0540-4356-c59c-fdeb3201ce5e" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Test Accuracy: 93.6%\n" + "Test Accuracy: 94.0%\n" ] } ], @@ -2858,7 +2780,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "gsJyOFNTJNXf" }, "source": [ @@ -2869,7 +2790,7 @@ "metadata": { "colab": { "collapsed_sections": [], - "name": "Snorkel.ipynb", + "name": "06_Snorkel.ipynb", "provenance": [] }, "kernelspec": { @@ -2887,7 +2808,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.6.13" } }, "nbformat": 4, From 63e133ef803aa08d4af86685adbd46d5a359256f Mon Sep 17 00:00:00 2001 From: jatinpapreja <47968703+jatinpapreja@users.noreply.github.com> Date: Sun, 27 Jun 2021 12:25:58 +0530 Subject: [PATCH 2/2] [Ch2Nb05] Fixed some errors 1. Changed comments. 2. Added dependency. --- Ch2/05_Data_Augmentation_Using_NLPaug.ipynb | 182 ++++++++++---------- 1 file changed, 95 insertions(+), 87 deletions(-) diff --git a/Ch2/05_Data_Augmentation_Using_NLPaug.ipynb b/Ch2/05_Data_Augmentation_Using_NLPaug.ipynb index 9f65e32..cca099b 100644 --- a/Ch2/05_Data_Augmentation_Using_NLPaug.ipynb +++ b/Ch2/05_Data_Augmentation_Using_NLPaug.ipynb @@ -3,7 +3,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "yavI9mt4gayF" }, "source": [ @@ -21,12 +20,10 @@ "start_time": "2021-04-03T11:15:01.468101Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 610 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "cF5zJdr-kAPY", - "outputId": "7feb4f81-fc71-4634-f9e8-90a7e060888b" + "outputId": "ffc73813-05cf-425b-c990-06437f18572e" }, "outputs": [ { @@ -34,14 +31,25 @@ "output_type": "stream", "text": [ "Collecting nlpaug==0.0.14\n", - " Downloading nlpaug-0.0.14-py3-none-any.whl (101 kB)\n", - "Installing collected packages: nlpaug\n", + "\u001b[?25l Downloading https://files.pythonhosted.org/packages/1f/6c/ca85b6bd29926561229e8c9f677c36c65db9ef1947bfc175e6641bc82ace/nlpaug-0.0.14-py3-none-any.whl (101kB)\n", + "\r", + "\u001b[K |███▎ | 10kB 11.3MB/s eta 0:00:01\r", + "\u001b[K |██████▌ | 20kB 16.9MB/s eta 0:00:01\r", + "\u001b[K |█████████▊ | 30kB 21.2MB/s eta 0:00:01\r", + "\u001b[K |█████████████ | 40kB 23.5MB/s eta 0:00:01\r", + "\u001b[K |████████████████▏ | 51kB 16.6MB/s eta 0:00:01\r", + "\u001b[K |███████████████████▍ | 61kB 18.7MB/s eta 0:00:01\r", + "\u001b[K |██████████████████████▋ | 71kB 12.7MB/s eta 0:00:01\r", + "\u001b[K |█████████████████████████▉ | 81kB 13.5MB/s eta 0:00:01\r", + "\u001b[K |█████████████████████████████ | 92kB 13.3MB/s eta 0:00:01\r", + "\u001b[K |████████████████████████████████| 102kB 7.3MB/s \n", + "\u001b[?25hInstalling collected packages: nlpaug\n", "Successfully installed nlpaug-0.0.14\n" ] } ], "source": [ - "#Installing the nlpaug package\n", + "# Installing the nlpaug package\n", "!pip install nlpaug==0.0.14" ] }, @@ -53,13 +61,11 @@ "end_time": "2021-04-03T11:15:11.595619Z", "start_time": "2021-04-03T11:15:11.593618Z" }, - "colab": {}, - "colab_type": "code", "id": "8yhkOl3cgZ28" }, "outputs": [], "source": [ - "#this will be the base text which we will be using throughout this notebook\n", + "# This will be the base text which we will be using throughout this notebook\n", "text=\"The quick brown fox jumps over the lazy dog .\"" ] }, @@ -71,16 +77,24 @@ "end_time": "2021-04-03T11:15:15.458928Z", "start_time": "2021-04-03T11:15:12.067195Z" }, - "colab": {}, - "colab_type": "code", - "id": "ekFhzIWHUmoj" + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ekFhzIWHUmoj", + "outputId": "c0864316-cb76-4be7-d2c2-961a6e526b0c" }, "outputs": [ { - "name": "stderr", + "name": "stdout", "output_type": "stream", "text": [ - "Cloning into 'nlpaug'...\n" + "Cloning into 'nlpaug'...\n", + "remote: Enumerating objects: 4843, done.\u001b[K\n", + "remote: Counting objects: 100% (370/370), done.\u001b[K\n", + "remote: Compressing objects: 100% (244/244), done.\u001b[K\n", + "remote: Total 4843 (delta 257), reused 209 (delta 126), pack-reused 4473\u001b[K\n", + "Receiving objects: 100% (4843/4843), 3.01 MiB | 15.26 MiB/s, done.\n", + "Resolving deltas: 100% (3419/3419), done.\n" ] } ], @@ -99,7 +113,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "-Xo3CzNhh-zU" }, "source": [ @@ -120,12 +133,10 @@ "start_time": "2021-04-03T11:15:15.459929Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 86 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "lfAaokTmjzak", - "outputId": "cfc78e2c-b41c-44a9-da1a-23c33a4c142c" + "outputId": "1828ed1c-b088-43a2-d6a5-77a57970691f" }, "outputs": [ { @@ -135,16 +146,16 @@ "Original:\n", "The quick brown fox jumps over the lazy dog .\n", "Augmented Texts:\n", - "['The quicr brown fox jumps ovek the lazy dog .', 'The quick bkown fox jumps over the lazy dog .', 'The quicr brown fox jumps over the lazy do9 .']\n" + "['The quicr brown fox jumps over the 1azy dog .', 'The quick brown fux jump8 over the lazy dog .', 'The quick brown f0x jumps ovek the lazy dog .']\n" ] } ], "source": [ - "#OCR augmenter\n", - "#import nlpaug.augmenter.char as nac\n", + "# OCR augmenter\n", + "# import nlpaug.augmenter.char as nac\n", "\n", "aug = nac.OcrAug() \n", - "augmented_texts = aug.augment(text, n=3) #specifying n=3 gives us only 3 augmented versions of the sentence.\n", + "augmented_texts = aug.augment(text, n=3) # specifying n=3 gives us only 3 augmented versions of the sentence.\n", "\n", "print(\"Original:\")\n", "print(text)\n", @@ -162,12 +173,10 @@ "start_time": "2021-04-03T11:15:16.880652Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 86 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "fKQCpS35j9Ie", - "outputId": "adcb28f2-a6c4-46f6-e780-d52dade97a1b" + "outputId": "a158e332-24bb-4e13-e8c4-a97ffcae3d65" }, "outputs": [ { @@ -177,17 +186,17 @@ "Original:\n", "The quick brown fox jumps over the lazy dog .\n", "Augmented Text:\n", - "['The quick brown fox ,umps over the lazy dog .', 'The quivk browm fox jumps over the Kazy dog .', 'The quKck brown fox jumps over the lazy dog .']\n" + "['The quick browj fox jumps over the lazy dog .', 'The Wuick brown fox jumps over the lazy dog .', 'The qu*ck brown fox jumps ovfr the lazy dog .']\n" ] } ], "source": [ - "#Keyboard Augmenter\n", - "#import nlpaug.augmenter.word as naw\n", + "# Keyboard Augmenter\n", + "# import nlpaug.augmenter.word as naw\n", "\n", "\n", "aug = nac.KeyboardAug()\n", - "augmented_text = aug.augment(text, n=3) #specifying n=3 gives us only 3 augmented versions of the sentence.\n", + "augmented_text = aug.augment(text, n=3) # specifying n=3 gives us only 3 augmented versions of the sentence.\n", "\n", "print(\"Original:\")\n", "print(text)\n", @@ -199,7 +208,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "XbfPMwZWmper" }, "source": [ @@ -209,7 +217,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "MufLJXsQm4i1" }, "source": [ @@ -221,7 +228,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "Tc_K1-niTGFP" }, "source": [ @@ -230,41 +236,48 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "metadata": { - "ExecuteTime": { - "end_time": "2021-04-03T11:16:58.980739Z", - "start_time": "2021-04-03T11:16:58.532879Z" - }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 208 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", - "id": "2Qzmv4QCYrJe", - "outputId": "2929c51c-5e3c-4a0a-bf7f-7847c48f19f9" + "id": "3QzwzH2dKam_", + "outputId": "7a345dd5-971d-412f-aa62-d6c21de36ee2" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "100% [............................................................................] 543624 / 543624" + "Collecting wget\n", + " Downloading https://files.pythonhosted.org/packages/47/6a/62e288da7bcda82b935ff0c6cfe542970f04e29c756b0e147251b2fb251f/wget-3.2.zip\n", + "Building wheels for collected packages: wget\n", + " Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for wget: filename=wget-3.2-cp37-none-any.whl size=9675 sha256=d15acba18a51c7f3c52521a590b6a1770e658c4c37445f6236e10cfb45d35159\n", + " Stored in directory: /root/.cache/pip/wheels/40/15/30/7d8f7cea2902b4db79e3fea550d7d7b85ecb27ef992b618f3f\n", + "Successfully built wget\n", + "Installing collected packages: wget\n", + "Successfully installed wget-3.2\n" ] - }, - { - "data": { - "text/plain": [ - "'spelling_en.txt'" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" } ], "source": [ - "#Downloading the required txt file\n", + "!pip install wget" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "ExecuteTime": { + "end_time": "2021-04-03T11:16:58.980739Z", + "start_time": "2021-04-03T11:16:58.532879Z" + }, + "id": "2Qzmv4QCYrJe" + }, + "outputs": [], + "source": [ + "# Downloading the required txt file\n", "import wget\n", "\n", "if not os.path.exists(\"spelling_en.txt\"):\n", @@ -275,19 +288,17 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "metadata": { "ExecuteTime": { "end_time": "2021-04-03T11:17:00.723918Z", "start_time": "2021-04-03T11:17:00.619823Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 86 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "gOHrgDIill2F", - "outputId": "875ad100-7492-47f2-a9a1-ea90565feb93" + "outputId": "856f34aa-cdab-49a3-fd5c-f6de0928bd87" }, "outputs": [ { @@ -297,12 +308,12 @@ "Original:\n", "The quick brown fox jumps over the lazy dog .\n", "Augmented Texts:\n", - "Tha qchick brown fox jumps over athe lazy dog .\n" + "The quick browne fox jumps over th laizy dog .\n" ] } ], "source": [ - "#Substitute word by spelling mistake words dictionary\n", + "# Substitute word by spelling mistake words dictionary\n", "aug = naw.SpellingAug('spelling_en.txt')\n", "augmented_texts = aug.augment(text)\n", "print(\"Original:\")\n", @@ -314,7 +325,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "eaeQOtVqTQKG" }, "source": [ @@ -323,12 +333,17 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 9, "metadata": { "ExecuteTime": { "end_time": "2021-04-03T11:42:53.178843Z", "start_time": "2021-04-03T11:42:53.163829Z" - } + }, + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "jIB9bMi5KWZ5", + "outputId": "62929df1-47f5-4273-965b-18e7f04793e1" }, "outputs": [ { @@ -346,14 +361,14 @@ "gn_vec_path = \"GoogleNews-vectors-negative300.bin\"\n", "if not os.path.exists(\"GoogleNews-vectors-negative300.bin\"):\n", " if not os.path.exists(\"../Ch3/GoogleNews-vectors-negative300.bin\"):\n", - " #Downloading the reqired model\n", + " # Downloading the reqired model\n", " if not os.path.exists(\"../Ch3/GoogleNews-vectors-negative300.bin.gz\"):\n", " if not os.path.exists(\"GoogleNews-vectors-negative300.bin.gz\"):\n", " wget.download(\"https://s3.amazonaws.com/dl4j-distribution/GoogleNews-vectors-negative300.bin.gz\")\n", " gn_vec_zip_path = \"GoogleNews-vectors-negative300.bin.gz\"\n", " else:\n", " gn_vec_zip_path = \"../Ch3/GoogleNews-vectors-negative300.bin.gz\"\n", - " #Extracting the required model\n", + " # Extracting the required model\n", " with gzip.open(gn_vec_zip_path, 'rb') as f_in:\n", " with open(gn_vec_path, 'wb') as f_out:\n", " shutil.copyfileobj(f_in, f_out)\n", @@ -366,7 +381,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "Jf_QHk-SgegN" }, "source": [ @@ -375,19 +389,17 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 10, "metadata": { "ExecuteTime": { "end_time": "2021-04-03T11:44:12.444755Z", "start_time": "2021-04-03T11:43:07.255745Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 86 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "ffUb6s-XTOsQ", - "outputId": "c4e66181-555c-4c2a-ce02-750592b3a676" + "outputId": "353c43d9-f804-4c1b-de5e-cee6f28cb7f4" }, "outputs": [ { @@ -397,7 +409,7 @@ "Original:\n", "The quick brown fox jumps over the lazy dog .\n", "Augmented Text:\n", - "The quick GlobeOp brown fox jumps over Exchange the Khulna lazy dog .\n" + "borne The quick obiter brown fox jumps Ahmed over the lazy dog .\n" ] } ], @@ -416,7 +428,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "kUB3Nd4Wghd0" }, "source": [ @@ -425,19 +436,17 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 11, "metadata": { "ExecuteTime": { "end_time": "2021-04-03T11:44:12.948639Z", "start_time": "2021-04-03T11:44:12.446757Z" }, "colab": { - "base_uri": "https://localhost:8080/", - "height": 86 + "base_uri": "https://localhost:8080/" }, - "colab_type": "code", "id": "pSeZNfQRfy2l", - "outputId": "37432ba5-41cd-4a6f-ffc9-8e4ef8b504af" + "outputId": "52a3eeea-c179-4de5-bb0a-9acf85de16e1" }, "outputs": [ { @@ -447,7 +456,7 @@ "Original:\n", "The quick brown fox jumps over the lazy dog .\n", "Augmented Text:\n", - "Though quick brown fox Leaping over it lazy dog .\n" + "The perfectly_timed brown fox jumps Within the lazy basset_hound .\n" ] } ], @@ -465,7 +474,6 @@ { "cell_type": "markdown", "metadata": { - "colab_type": "text", "id": "reALNlOuDI9u" }, "source": [ @@ -478,7 +486,7 @@ "colab": { "collapsed_sections": [], "machine_shape": "hm", - "name": "Data_Augmentation_Using_NLPaug.ipynb", + "name": "05_Data_Augmentation_Using_NLPaug.ipynb", "provenance": [] }, "kernelspec": { @@ -496,7 +504,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.7.4" } }, "nbformat": 4,