Update README.md

Author: sturex

README.md

@@ -1,24 +1,24 @@
-##With this sample you`ll be able to:
+## With this sample you`ll be able to:
 * get order book (Level II, market depth) from [BitMEX](https://www.bitmex.com) and save as json structures in day-lenght files
 * generate trading signals [BUY, SELL, WAIT] on orderbooks (not only BitMEX\`s) with or without help of sequential neural network
 * create training dataset for neural network from presaved orderbooks
 * create, train, save and restore neural network with input data of orderbooks (not only BitMEX`s)
 * perform backtest trading with output of trades
 
-###Limitations
+### Limitations
 * [BitMEX](https://www.bitmex.com) only and [XBTUSD](https://www.bitmex.com/app/contract/XBTUSD) data fetching only are provided. The source connection code taken from [Python Adapter for BitMEX Realtime Data](https://github.com/BitMEX/api-connectors/tree/master/official-ws/python)
 * Code works correctly only for 100-depth order books.
 * Neural network has voluntaristic rigid architecture where you can operate only number of layers and neurons quantity. Input layer must contain 100 neurons, output layer 2 neurons.
 * No commissions, fees etc. are calculated while backtesting. Result trades must be extra analyzed.
 
 
-##Installation
+## Installation
 ```
 pip install -r requirements.txt
 ```
 
-##Use cases
-####Retrieving order books ([Bitmex](https://www.bitmex.com) only)
+## Use cases
+#### Retrieving order books ([Bitmex](https://www.bitmex.com) only)
 Just run code below with your [API-key credentials to BitMEX](https://www.bitmex.com/app/apiKeysUsage).
 On every update of market 100-depth order book is writing to disk.
 [Bid-ask spread](https://en.wikipedia.org/wiki/Bid-ask_spread) is in the middle of order book. New trading day starts with new file.
@@ -35,7 +35,7 @@ bitmex.exit()
 ```
 
 
-####Dataset creation for neural network training
+#### Dataset creation for neural network training
 
 ```python
 from OrderBookContainer import *
@@ -49,7 +49,7 @@ for in_file in input_files:
 As a result the script will create Datasets subfolder with \*.ds files. 
 
 
-####Neural network creation, training and saving for next time use
+#### Neural network creation, training and saving for next time use
 
 My goal is just to show that neural networks work without price movement analysis but only on current market timestamp (== order book) analysis. 
 
@@ -74,27 +74,27 @@ nwk.train(datasets_folder)
 nwk.save_model('full_path_to_file.h5')
 ```
 
-####Trading signal generation
+#### Trading signal generation
 
 You can generate trading signal with possible values of [BUY, SELL, WAIT] with order book analysis only. 
 On every *orderbook* you get from exchange or read from file signal can be generated with code below.
 *threshold* is floating point value in range [0, 1]. The less the value the more signals you get. 
-######Neural generator
+###### Neural generator
 
 ```python
 from Generators import sample_generator_n
 nwk = TurexNetwork.TurexNetwork()
 nwk.load_model('model_from_code_above.h5')
 signal = sample_generator_n(nwk, orderbook.volumes, threshold)
 ```
-######Simple generator
+###### Simple generator
 ```python
 from Generators import sample_generator
 signal = sample_generator(orderbook.volumes, threshold)
 ```
 
 
-####Backtesting
+#### Backtesting
 The mean of *threshold* is described above.
 
 ```python