Added 301 rules for old articles

13 files changed, 1028 insertions, 1 deletions

diff --git a/src/experiments/encoding-binary-data-into-dna-sequence.md b/src/experiments/encoding-binary-data-into-dna-sequence.md
index cc42bd7..cdff15f 100644
--- a/src/experiments/encoding-binary-data-into-dna-sequence.md
+++ b/src/experiments/encoding-binary-data-into-dna-sequence.md
@@ -1,4 +1,5 @@
 title: Encoding binary data into DNA sequence
+description: Imagine a world where you could go outside and take a leaf from a tree and put it through your personal DNA sequencer and get data like music, videos or computer programs from it
 date: 2019-01-03
 tags: experiment
 hide: false
diff --git a/src/experiments/profiling-python-web-applications-with-visual-tools.md b/src/experiments/profiling-python-web-applications-with-visual-tools.md
index 29e16d7..58d85bf 100644
--- a/src/experiments/profiling-python-web-applications-with-visual-tools.md
+++ b/src/experiments/profiling-python-web-applications-with-visual-tools.md
@@ -1,4 +1,5 @@
 title: Profiling Python web applications with visual tools
+description: Missing link when debugging and profiling python web application
 date: 2017-04-21
 tags: experiment
 hide: false
diff --git a/src/experiments/simple-iot-application.md b/src/experiments/simple-iot-application.md
index b8744e6..1543e52 100644
--- a/src/experiments/simple-iot-application.md
+++ b/src/experiments/simple-iot-application.md
@@ -1,4 +1,5 @@
 title: Simple IOT application supported by real-time monitoring and data history
+description: Develop simple IOT application with Arduino MKR1000 and Python
 date: 2017-08-11
 tags: experiment
 hide: false
diff --git a/src/experiments/using-digitalocean-spaces-object-storage-with-fuse.md b/src/experiments/using-digitalocean-spaces-object-storage-with-fuse.md
index bc00d1e..ab0079f 100644
--- a/src/experiments/using-digitalocean-spaces-object-storage-with-fuse.md
+++ b/src/experiments/using-digitalocean-spaces-object-storage-with-fuse.md
@@ -1,4 +1,5 @@
 title: Using DigitalOcean Spaces Object Storage with FUSE
+description: Using DigitalOcean Spaces Object Storage with FUSE
 date: 2018-01-16
 tags: experiment
 hide: false
diff --git a/src/experiments/using-sentiment-analysis-for-click-bait-detection-in-rss-feeds.md b/src/experiments/using-sentiment-analysis-for-click-bait-detection-in-rss-feeds.md
new file mode 100644
index 0000000..c27c6d0
--- /dev/null
+++ b/src/experiments/using-sentiment-analysis-for-click-bait-detection-in-rss-feeds.md
@@ -0,0 +1,86 @@
+title: Using sentiment analysis for click‑bait detection in RSS feeds
+description: Using Python with sentiment analysis to detect if titles in RSS feeds are click-bait
+date: 2019-10-19
+tags: experiment
+hide: false
+----
+
+## Initial thoughts
+
+One of the things that interested me for a while now is  if major well established news sites use click bait titles to drive additional traffic to their sites and generate additional impressions.
+
+Goal is to see how article titles and actual content of article differ from each other and see if titles are click-baited.
+
+## Preparing and cleaning data
+
+For this example I opted to just use RSS feed from a new website and decided to go with [The Guardian](https://www.theguardian.com) World news. While this gets us limited data (~40) articles and also description (actual content) is trimmed this really doesn't reflect the actual article contents.
+
+To get better content I could use web scraping and use RSS as link list and fetch contents directly from website, but for this simple example this will suffice.
+
+There are couple of requirements we need to install before we continue:
+
+- `pip3 install feedparser` (parses RSS feed from url)
+- `pip3 install vaderSentiment` (does sentiment polarity analysis)
+- `pip3 install matplotlib` (plots chart of results)
+
+So first we need to fetch RSS data and sanitize HTML content from description.
+
+```python
+import re
+import feedparser
+
+feed_url = "https://www.theguardian.com/world/rss"
+feed = feedparser.parse(feed_url)
+
+for item in feed.import re:
+    # sanitize html
+    item.description = re.sub('<[^<]+?>', '', item.description)
+```
+
+## Perform sentiment analysis
+
+Since we now have cleaned up data in our `feed.entries` object we can start with performing sentiment analysis.
+
+There are many sentiment analysis libraries available that range from rule-based sentiment analysis up to machine learning supported analysis. To keep things simple I decided to use rule-based analysis library [vaderSentiment](https://github.com/cjhutto/vaderSentiment) from [C.J. Hutto](https://github.com/cjhutto). Really nice library and quite easy to use.
+
+```python
+from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+analyser = SentimentIntensityAnalyzer()
+
+sentiment_results = []
+for item in feed.entries:
+    sentiment_title = analyser.polarity_scores(item.title)
+    sentiment_description = analyser.polarity_scores(item.description)
+    sentiment_results.append([sentiment_title['compound'], sentiment_description['compound']])
+```
+
+Now that we have this data in a shape that is compatible with matplotlib we can plot results to see the difference between title and description sentiment of an article.
+
+```python
+import matplotlib.pyplot as plt
+
+plt.rcParams['figure.figsize'] = (15, 3)
+plt.plot(sentiment_results, drawstyle='steps')
+plt.title('Sentiment analysis relationship between title and description (Guardian World News)')
+plt.legend(['title', 'description'])
+plt.show()
+```
+
+## Results and assets
+
+1. Because of the small sample size further conclusions are impossible to make.
+2. Rule-based approach may not be the best way of doing this. By using deep learning we would be able to get better insights.
+3. **Next step would be to** periodically fetch RSS items and store them over a longer period of time and then perform analysis again and use either machine learning or deep learning on top of it.
+
+![Relationship between title and description](/files/sentiment-analysis/guardian-sa-title-desc-relationship.png)
+
+Figure above displays difference between title and description sentiment for specific RSS feed item. 1 means positive and -1 means negative sentiment.
+
+[» Download Jupyter Notebook](/files/sentiment-analysis/sentiment-analysis.ipynb)
+
+## Going further
+
+- [Twitter Sentiment Analysis by Bryan Schwierzke](https://github.com/bswiss/news_mood)
+- [AFINN-based sentiment analysis for Node.js by Andrew Sliwinski](https://github.com/thisandagain/sentiment)
+- [Sentiment Analysis with LSTMs in Tensorflow by Adit Deshpande](https://github.com/adeshpande3/LSTM-Sentiment-Analysis)
+- [Sentiment analysis on tweets using Naive Bayes, SVM, CNN, LSTM, etc. by Abdul Fatir](https://github.com/abdulfatir/twitter-sentiment-analysis)
diff --git a/src/files/sentiment-analysis/.ipynb_checkpoints/TF Test-checkpoint.ipynb b/src/files/sentiment-analysis/.ipynb_checkpoints/TF Test-checkpoint.ipynb
new file mode 100644
index 0000000..e2a85c4
--- /dev/null
+++ b/src/files/sentiment-analysis/.ipynb_checkpoints/TF Test-checkpoint.ipynb
@@ -0,0 +1,588 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2.0.0-beta1\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint8 = np.dtype([(\"qint8\", np.int8, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_quint8 = np.dtype([(\"quint8\", np.uint8, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint16 = np.dtype([(\"qint16\", np.int16, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_quint16 = np.dtype([(\"quint16\", np.uint16, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  _np_qint32 = np.dtype([(\"qint32\", np.int32, 1)])\n",
+      "/home/m/.local/lib/python3.7/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.\n",
+      "  np_resource = np.dtype([(\"resource\", np.ubyte, 1)])\n"
+     ]
+    }
+   ],
+   "source": [
+    "import tensorflow as tf\n",
+    "from tensorflow import keras\n",
+    "\n",
+    "# Helper libraries\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "print(tf.__version__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from numpy import genfromtxt\n",
+    "data = genfromtxt('data.csv', delimiter=',')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_input = data[:,0:3]\n",
+    "data_labels = data[:,3]\n",
+    "\n",
+    "#data_input = np.transpose(data_input)\n",
+    "#data_labels = np.transpose(data_labels)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(600, 3)\n",
+      "[1.e-01 1.e+00 3.e+02]\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(np.shape(data_input))\n",
+    "print(data_input[2])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "print(len(data_input))\n",
+    "print(len(data_labels))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(500, 3)\n",
+      "(100, 3)\n",
+      "(500,)\n",
+      "(100,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_input_train = data_input[0:500,:]\n",
+    "data_input_test = data_input[500:,:]\n",
+    "\n",
+    "data_labels_train = data_labels[0:500]\n",
+    "data_labels_test = data_labels[500:]\n",
+    "\n",
+    "print(np.shape(data_input_train))\n",
+    "print(np.shape(data_input_test))\n",
+    "\n",
+    "print(np.shape(data_labels_train))\n",
+    "print(np.shape(data_labels_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = keras.Sequential([\n",
+    "    keras.layers.Dense(128, activation='relu', input_shape=[3]),\n",
+    "    keras.layers.Dense(512, activation='relu'),\n",
+    "    keras.layers.Dense(512, activation='relu'),\n",
+    "    keras.layers.Dense(512, activation='relu'),\n",
+    "    keras.layers.Dense(128, activation='relu'),\n",
+    "    keras.layers.Dense(1)\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "optimizer = tf.keras.optimizers.RMSprop(0.001)\n",
+    "model.compile(loss='mse',\n",
+    "                optimizer=optimizer,\n",
+    "                metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train on 500 samples\n",
+      "Epoch 1/100\n",
+      "500/500 [==============================] - 0s 399us/sample - loss: 247.2794 - accuracy: 0.0040\n",
+      "Epoch 2/100\n",
+      "500/500 [==============================] - 0s 121us/sample - loss: 4.2495 - accuracy: 0.0060\n",
+      "Epoch 3/100\n",
+      "500/500 [==============================] - 0s 131us/sample - loss: 1.8787 - accuracy: 0.0040\n",
+      "Epoch 4/100\n",
+      "500/500 [==============================] - 0s 121us/sample - loss: 0.4284 - accuracy: 0.0060\n",
+      "Epoch 5/100\n",
+      "500/500 [==============================] - 0s 107us/sample - loss: 4.7904 - accuracy: 0.0080\n",
+      "Epoch 6/100\n",
+      "500/500 [==============================] - 0s 113us/sample - loss: 0.0819 - accuracy: 0.0040\n",
+      "Epoch 7/100\n",
+      "500/500 [==============================] - 0s 108us/sample - loss: 1.6904 - accuracy: 0.0040\n",
+      "Epoch 8/100\n",
+      "500/500 [==============================] - 0s 116us/sample - loss: 0.1761 - accuracy: 0.0040\n",
+      "Epoch 9/100\n",
+      "500/500 [==============================] - 0s 142us/sample - loss: 0.1135 - accuracy: 0.0040\n",
+      "Epoch 10/100\n",
+      "500/500 [==============================] - 0s 124us/sample - loss: 0.4387 - accuracy: 0.0040\n",
+      "Epoch 11/100\n",
+      "500/500 [==============================] - 0s 112us/sample - loss: 0.0815 - accuracy: 0.0040\n",
+      "Epoch 12/100\n",
+      "500/500 [==============================] - 0s 117us/sample - loss: 0.1725 - accuracy: 0.0040\n",
+      "Epoch 13/100\n",
+      "500/500 [==============================] - 0s 119us/sample - loss: 0.1487 - accuracy: 0.0040\n",
+      "Epoch 14/100\n",
+      "500/500 [==============================] - 0s 111us/sample - loss: 0.0720 - accuracy: 0.0040\n",
+      "Epoch 15/100\n",
+      "500/500 [==============================] - 0s 111us/sample - loss: 0.3110 - accuracy: 0.0040\n",
+      "Epoch 16/100\n",
+      "500/500 [==============================] - 0s 128us/sample - loss: 0.0947 - accuracy: 0.0040\n",
+      "Epoch 17/100\n",
+      "500/500 [==============================] - 0s 133us/sample - loss: 0.0739 - accuracy: 0.0040\n",
+      "Epoch 18/100\n",
+      "500/500 [==============================] - 0s 131us/sample - loss: 0.1353 - accuracy: 0.0060\n",
+      "Epoch 19/100\n",
+      "500/500 [==============================] - 0s 135us/sample - loss: 0.0837 - accuracy: 0.0040\n",
+      "Epoch 20/100\n",
+      "500/500 [==============================] - 0s 130us/sample - loss: 0.0754 - accuracy: 0.0040\n",
+      "Epoch 21/100\n",
+      "500/500 [==============================] - 0s 118us/sample - loss: 0.0840 - accuracy: 0.0040\n",
+      "Epoch 22/100\n",
+      "500/500 [==============================] - 0s 115us/sample - loss: 0.1105 - accuracy: 0.0040\n",
+      "Epoch 23/100\n",
+      "500/500 [==============================] - 0s 116us/sample - loss: 0.0651 - accuracy: 0.0040\n",
+      "Epoch 24/100\n",
+      "500/500 [==============================] - 0s 109us/sample - loss: 0.0615 - accuracy: 0.0040\n",
+      "Epoch 25/100\n",
+      "500/500 [==============================] - 0s 118us/sample - loss: 0.0656 - accuracy: 0.0040\n",
+      "Epoch 26/100\n",
+      "500/500 [==============================] - 0s 113us/sample - loss: 0.0695 - accuracy: 0.0040\n",
+      "Epoch 27/100\n",
+      "500/500 [==============================] - 0s 116us/sample - loss: 0.0585 - accuracy: 0.0040\n",
+      "Epoch 28/100\n",
+      "500/500 [==============================] - 0s 118us/sample - loss: 0.1300 - accuracy: 0.0040\n",
+      "Epoch 29/100\n",
+      "500/500 [==============================] - 0s 112us/sample - loss: 0.0567 - accuracy: 0.0040\n",
+      "Epoch 30/100\n",
+      "500/500 [==============================] - 0s 137us/sample - loss: 0.0647 - accuracy: 0.0040\n",
+      "Epoch 31/100\n",
+      "500/500 [==============================] - 0s 130us/sample - loss: 0.0559 - accuracy: 0.0040\n",
+      "Epoch 32/100\n",
+      "500/500 [==============================] - 0s 130us/sample - loss: 0.0576 - accuracy: 0.0040\n",
+      "Epoch 33/100\n",
+      "500/500 [==============================] - 0s 128us/sample - loss: 0.0578 - accuracy: 0.0040\n",
+      "Epoch 34/100\n",
+      "500/500 [==============================] - 0s 130us/sample - loss: 0.0512 - accuracy: 0.0040\n",
+      "Epoch 35/100\n",
+      "500/500 [==============================] - 0s 114us/sample - loss: 0.0601 - accuracy: 0.0040\n",
+      "Epoch 36/100\n",
+      "500/500 [==============================] - 0s 111us/sample - loss: 0.0531 - accuracy: 0.0040\n",
+      "Epoch 37/100\n",
+      "500/500 [==============================] - 0s 130us/sample - loss: 0.0532 - accuracy: 0.0040\n",
+      "Epoch 38/100\n",
+      "500/500 [==============================] - 0s 131us/sample - loss: 0.0480 - accuracy: 0.0040\n",
+      "Epoch 39/100\n",
+      "500/500 [==============================] - 0s 136us/sample - loss: 0.0503 - accuracy: 0.0040\n",
+      "Epoch 40/100\n",
+      "500/500 [==============================] - 0s 134us/sample - loss: 0.0468 - accuracy: 0.0040\n",
+      "Epoch 41/100\n",
+      "500/500 [==============================] - 0s 115us/sample - loss: 0.0509 - accuracy: 0.0040\n",
+      "Epoch 42/100\n",
+      "500/500 [==============================] - 0s 109us/sample - loss: 0.0453 - accuracy: 0.0040\n",
+      "Epoch 43/100\n",
+      "500/500 [==============================] - 0s 111us/sample - loss: 0.0484 - accuracy: 0.0040\n",
+      "Epoch 44/100\n",
+      "500/500 [==============================] - 0s 104us/sample - loss: 0.0458 - accuracy: 0.0040\n",
+      "Epoch 45/100\n",
+      "500/500 [==============================] - 0s 110us/sample - loss: 0.0481 - accuracy: 0.0040\n",
+      "Epoch 46/100\n",
+      "500/500 [==============================] - 0s 114us/sample - loss: 0.0468 - accuracy: 0.0060\n",
+      "Epoch 47/100\n",
+      "500/500 [==============================] - 0s 124us/sample - loss: 0.0473 - accuracy: 0.0060\n",
+      "Epoch 48/100\n",
+      "500/500 [==============================] - 0s 137us/sample - loss: 0.0455 - accuracy: 0.0040\n",
+      "Epoch 49/100\n",
+      "500/500 [==============================] - 0s 125us/sample - loss: 0.0431 - accuracy: 0.0060\n",
+      "Epoch 50/100\n",
+      "500/500 [==============================] - 0s 132us/sample - loss: 0.0432 - accuracy: 0.0060\n",
+      "Epoch 51/100\n",
+      "500/500 [==============================] - 0s 116us/sample - loss: 0.0484 - accuracy: 0.0060\n",
+      "Epoch 52/100\n",
+      "500/500 [==============================] - 0s 112us/sample - loss: 0.0482 - accuracy: 0.0040\n",
+      "Epoch 53/100\n",
+      "500/500 [==============================] - 0s 117us/sample - loss: 0.0444 - accuracy: 0.0060\n",
+      "Epoch 54/100\n",
+      "500/500 [==============================] - 0s 109us/sample - loss: 0.0469 - accuracy: 0.0060\n",
+      "Epoch 55/100\n",
+      "500/500 [==============================] - 0s 106us/sample - loss: 0.0427 - accuracy: 0.0040\n",
+      "Epoch 56/100\n",
+      "500/500 [==============================] - 0s 110us/sample - loss: 0.0433 - accuracy: 0.0040\n",
+      "Epoch 57/100\n",
+      "500/500 [==============================] - 0s 102us/sample - loss: 0.0437 - accuracy: 0.0060\n",
+      "Epoch 58/100\n",
+      "500/500 [==============================] - 0s 117us/sample - loss: 0.0425 - accuracy: 0.0040\n",
+      "Epoch 59/100\n",
+      "500/500 [==============================] - 0s 105us/sample - loss: 0.0418 - accuracy: 0.0040\n",
+      "Epoch 60/100\n",
+      "500/500 [==============================] - 0s 109us/sample - loss: 0.0397 - accuracy: 0.0040\n",
+      "Epoch 61/100\n",
+      "500/500 [==============================] - 0s 119us/sample - loss: 0.0507 - accuracy: 0.0040\n",
+      "Epoch 62/100\n",
+      "500/500 [==============================] - 0s 112us/sample - loss: 0.0402 - accuracy: 0.0060\n",
+      "Epoch 63/100\n",
+      "500/500 [==============================] - 0s 133us/sample - loss: 0.0397 - accuracy: 0.0040\n",
+      "Epoch 64/100\n",
+      "500/500 [==============================] - 0s 132us/sample - loss: 0.0427 - accuracy: 0.0060\n",
+      "Epoch 65/100\n",
+      "500/500 [==============================] - 0s 138us/sample - loss: 0.0398 - accuracy: 0.0040\n",
+      "Epoch 66/100\n",
+      "500/500 [==============================] - 0s 145us/sample - loss: 0.0375 - accuracy: 0.0060\n",
+      "Epoch 67/100\n",
+      "500/500 [==============================] - 0s 138us/sample - loss: 0.0402 - accuracy: 0.0060\n",
+      "Epoch 68/100\n",
+      "500/500 [==============================] - 0s 132us/sample - loss: 0.0388 - accuracy: 0.0080\n",
+      "Epoch 69/100\n",
+      "500/500 [==============================] - 0s 115us/sample - loss: 0.0375 - accuracy: 0.0080\n",
+      "Epoch 70/100\n",
+      "500/500 [==============================] - 0s 113us/sample - loss: 0.0384 - accuracy: 0.0040\n",
+      "Epoch 71/100\n",
+      "500/500 [==============================] - 0s 109us/sample - loss: 0.0360 - accuracy: 0.0080\n",
+      "Epoch 72/100\n",
+      "500/500 [==============================] - 0s 111us/sample - loss: 0.0350 - accuracy: 0.0080\n",
+      "Epoch 73/100\n",
+      "500/500 [==============================] - 0s 118us/sample - loss: 0.0370 - accuracy: 0.0060\n",
+      "Epoch 74/100\n",
+      "500/500 [==============================] - 0s 95us/sample - loss: 0.0354 - accuracy: 0.0080\n",
+      "Epoch 75/100\n",
+      "500/500 [==============================] - 0s 102us/sample - loss: 0.0376 - accuracy: 0.0060\n",
+      "Epoch 76/100\n",
+      "500/500 [==============================] - 0s 106us/sample - loss: 0.0371 - accuracy: 0.0080\n",
+      "Epoch 77/100\n",
+      "500/500 [==============================] - 0s 100us/sample - loss: 0.0369 - accuracy: 0.0060\n",
+      "Epoch 78/100\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "500/500 [==============================] - 0s 98us/sample - loss: 0.0315 - accuracy: 0.0060\n",
+      "Epoch 79/100\n",
+      "500/500 [==============================] - 0s 97us/sample - loss: 0.0355 - accuracy: 0.0060\n",
+      "Epoch 80/100\n",
+      "500/500 [==============================] - 0s 100us/sample - loss: 0.0278 - accuracy: 0.0080\n",
+      "Epoch 81/100\n",
+      "500/500 [==============================] - 0s 99us/sample - loss: 0.0320 - accuracy: 0.0080\n",
+      "Epoch 82/100\n",
+      "500/500 [==============================] - 0s 99us/sample - loss: 0.0321 - accuracy: 0.0080\n",
+      "Epoch 83/100\n",
+      "500/500 [==============================] - 0s 94us/sample - loss: 0.0332 - accuracy: 0.0060\n",
+      "Epoch 84/100\n",
+      "500/500 [==============================] - 0s 106us/sample - loss: 0.0317 - accuracy: 0.0060\n",
+      "Epoch 85/100\n",
+      "500/500 [==============================] - 0s 103us/sample - loss: 0.0293 - accuracy: 0.0080\n",
+      "Epoch 86/100\n",
+      "500/500 [==============================] - 0s 107us/sample - loss: 0.0304 - accuracy: 0.0060\n",
+      "Epoch 87/100\n",
+      "500/500 [==============================] - 0s 101us/sample - loss: 0.0327 - accuracy: 0.0040\n",
+      "Epoch 88/100\n",
+      "500/500 [==============================] - 0s 100us/sample - loss: 0.0290 - accuracy: 0.0080\n",
+      "Epoch 89/100\n",
+      "500/500 [==============================] - 0s 123us/sample - loss: 0.0293 - accuracy: 0.0060\n",
+      "Epoch 90/100\n",
+      "500/500 [==============================] - 0s 104us/sample - loss: 0.0246 - accuracy: 0.0060\n",
+      "Epoch 91/100\n",
+      "500/500 [==============================] - 0s 124us/sample - loss: 0.0303 - accuracy: 0.0060\n",
+      "Epoch 92/100\n",
+      "500/500 [==============================] - 0s 129us/sample - loss: 0.0376 - accuracy: 0.0080\n",
+      "Epoch 93/100\n",
+      "500/500 [==============================] - 0s 122us/sample - loss: 0.0264 - accuracy: 0.0080\n",
+      "Epoch 94/100\n",
+      "500/500 [==============================] - 0s 102us/sample - loss: 0.0265 - accuracy: 0.0080\n",
+      "Epoch 95/100\n",
+      "500/500 [==============================] - 0s 108us/sample - loss: 0.0291 - accuracy: 0.0080\n",
+      "Epoch 96/100\n",
+      "500/500 [==============================] - 0s 101us/sample - loss: 0.0314 - accuracy: 0.0080\n",
+      "Epoch 97/100\n",
+      "500/500 [==============================] - 0s 95us/sample - loss: 0.0257 - accuracy: 0.0060\n",
+      "Epoch 98/100\n",
+      "500/500 [==============================] - 0s 100us/sample - loss: 0.0248 - accuracy: 0.0080\n",
+      "Epoch 99/100\n",
+      "500/500 [==============================] - 0s 94us/sample - loss: 0.0250 - accuracy: 0.0040\n",
+      "Epoch 100/100\n",
+      "500/500 [==============================] - 0s 106us/sample - loss: 0.0312 - accuracy: 0.0060\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<tensorflow.python.keras.callbacks.History at 0x7f55a3853f60>"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#model.fit(data_input_train, data_labels_train, validation_data=(data_input_test, data_labels_test), epochs=100)\n",
+    "model.fit(data_input_train, data_labels_train, epochs=100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "100/100 - 0s - loss: 0.0470 - accuracy: 0.0100\n",
+      "\n",
+      "Test accuracy: 0.01\n"
+     ]
+    }
+   ],
+   "source": [
+    "test_loss, test_acc = model.evaluate(data_input_test,  data_labels_test, verbose=2)\n",
+    "\n",
+    "print('\\nTest accuracy:', test_acc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0.3141548]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "input = np.array([0.46,2,136])\n",
+    "input.shape = (1,3)\n",
+    "\n",
+    "prediction = model.predict(input)\n",
+    "print(prediction)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = model.predict(data_input_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib qt \n",
+    "plt.plot(predictions)\n",
+    "plt.plot(data_labels_test, 'r')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 204,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib qt\n",
+    "a = data_labels_test - predictions\n",
+    "plt.plot(a[0])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 207,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib qt\n",
+    "a = data_labels_test - predictions\n",
+    "plt.plot(predictions)\n",
+    "plt.plot(data_labels_test, 'r')\n",
+    "plt.plot(a[0], 'g')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 180,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "-0.08489150602276586"
+      ]
+     },
+     "execution_count": 180,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np.average(a[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 182,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential_13\"\n",
+      "_________________________________________________________________\n",
+      "Layer (type)                 Output Shape              Param #   \n",
+      "=================================================================\n",
+      "dense_38 (Dense)             (None, 128)               512       \n",
+      "_________________________________________________________________\n",
+      "dense_39 (Dense)             (None, 512)               66048     \n",
+      "_________________________________________________________________\n",
+      "dense_40 (Dense)             (None, 512)               262656    \n",
+      "_________________________________________________________________\n",
+      "dense_41 (Dense)             (None, 512)               262656    \n",
+      "_________________________________________________________________\n",
+      "dense_42 (Dense)             (None, 128)               65664     \n",
+      "_________________________________________________________________\n",
+      "dense_43 (Dense)             (None, 1)                 129       \n",
+      "=================================================================\n",
+      "Total params: 657,665\n",
+      "Trainable params: 657,665\n",
+      "Non-trainable params: 0\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 183,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.save('my_model.h5')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/src/files/sentiment-analysis/.ipynb_checkpoints/sentiment-analysis-checkpoint.ipynb b/src/files/sentiment-analysis/.ipynb_checkpoints/sentiment-analysis-checkpoint.ipynb
new file mode 100644
index 0000000..2c0934c
--- /dev/null
+++ b/src/files/sentiment-analysis/.ipynb_checkpoints/sentiment-analysis-checkpoint.ipynb
@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Sentiment analysis of Guardian World News articles"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get articles from a website"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install rss parser dependency"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install feedparser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Parsing RSS feed for world news"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import feedparser\n",
+    "feed_url = \"https://www.theguardian.com/world/rss\"\n",
+    "feed = feedparser.parse(feed_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "for item in feed.entries:\n",
+    "    # sanitize html\n",
+    "    item.description = re.sub('<[^<]+?>', '', item.description)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Vader Sentiment library and perform sentiment analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install vaderSentiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n",
+    "analyser = SentimentIntensityAnalyzer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sentiment_results = []\n",
+    "for item in feed.entries:\n",
+    "    sentiment_title = analyser.polarity_scores(item.title)\n",
+    "    sentiment_description = analyser.polarity_scores(item.description)\n",
+    "    sentiment_results.append([sentiment_title['compound'], sentiment_description['compound']])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Matplotlib and visualize compound score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install matplotlib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "plt.rcParams['figure.figsize'] = (15, 3)\n",
+    "plt.plot(sentiment_results, drawstyle='steps')\n",
+    "plt.title('Sentiment analysis relationship between title and description (Guardian World News)')\n",
+    "plt.legend(['title', 'description'])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/src/files/sentiment-analysis/guardian-sa-title-desc-relationship.png b/src/files/sentiment-analysis/guardian-sa-title-desc-relationship.png
new file mode 100644
index 0000000..7195bbf
--- /dev/null
+++ b/src/files/sentiment-analysis/guardian-sa-title-desc-relationship.png
diff --git a/src/files/sentiment-analysis/sentiment-analysis.ipynb b/src/files/sentiment-analysis/sentiment-analysis.ipynb
new file mode 100644
index 0000000..2c0934c
--- /dev/null
+++ b/src/files/sentiment-analysis/sentiment-analysis.ipynb
@@ -0,0 +1,170 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Sentiment analysis of Guardian World News articles"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get articles from a website"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install rss parser dependency"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install feedparser"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Parsing RSS feed for world news"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import feedparser\n",
+    "feed_url = \"https://www.theguardian.com/world/rss\"\n",
+    "feed = feedparser.parse(feed_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "for item in feed.entries:\n",
+    "    # sanitize html\n",
+    "    item.description = re.sub('<[^<]+?>', '', item.description)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Vader Sentiment library and perform sentiment analysis"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install vaderSentiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n",
+    "analyser = SentimentIntensityAnalyzer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sentiment_results = []\n",
+    "for item in feed.entries:\n",
+    "    sentiment_title = analyser.polarity_scores(item.title)\n",
+    "    sentiment_description = analyser.polarity_scores(item.description)\n",
+    "    sentiment_results.append([sentiment_title['compound'], sentiment_description['compound']])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Install Matplotlib and visualize compound score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install matplotlib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "plt.rcParams['figure.figsize'] = (15, 3)\n",
+    "plt.plot(sentiment_results, drawstyle='steps')\n",
+    "plt.title('Sentiment analysis relationship between title and description (Guardian World News)')\n",
+    "plt.legend(['title', 'description'])\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/src/notes/golang-profiling-simplified.md b/src/notes/golang-profiling-simplified.md
index a49de67..c8c6f16 100644
--- a/src/notes/golang-profiling-simplified.md
+++ b/src/notes/golang-profiling-simplified.md
@@ -1,4 +1,5 @@
 title: Golang profiling simplified
+description: Golang profiling demystified
 date: 2017-03-07
 tags: blog
 hide: false
diff --git a/src/notes/simplifying-and-reducing-clutter.md b/src/notes/simplifying-and-reducing-clutter.md
index b435834..064f08b 100644
--- a/src/notes/simplifying-and-reducing-clutter.md
+++ b/src/notes/simplifying-and-reducing-clutter.md
@@ -1,4 +1,5 @@
 title: Simplifying and reducing clutter in my life and work
+description: Simplifying and reducing clutter in my life and work
 date: 2019-10-14
 tags: blog
 hide: false
diff --git a/src/notes/what-i-ve-learned-developing-ad-server.md b/src/notes/what-i-ve-learned-developing-ad-server.md
index 527f9d0..d1cc791 100644
--- a/src/notes/what-i-ve-learned-developing-ad-server.md
+++ b/src/notes/what-i-ve-learned-developing-ad-server.md
@@ -1,4 +1,5 @@
 title: What I've learned developing ad server
+description: Lessons I learned developing contextual ad server
 date: 2017-04-17
 tags: blog
 hide: false
diff --git a/src/static/style.css b/src/static/style.css
index 4654ae7..3cb585a 100644
--- a/src/static/style.css
+++ b/src/static/style.css
@@ -4,7 +4,7 @@ body {
 }
 
 main {
-    max-width: 680px;
+    max-width: 660px;
     padding: 20px 30px;
 }
 
@@ -68,6 +68,12 @@ th, td {
     padding: 5px 10px;
 }
 
+p.modified {
+    font-style: oblique;
+    font-size: 90%;
+    margin-top: 50px;
+}
+
 ::selection {
     background: #ff0;
     color: #000;