Cleanup

README.md

@@ -12,18 +12,24 @@ w = [4, 5, 6]
 print distance(v, w)
 print vector_mean([v, w])
 ```
-  
+
 Or can be run from the command line to get a demo of what it does (and to execute the examples from the book):
 
 ```bat
 python recommender_systems.py
-```  
+```
 
 Additionally, I've collected all the [links](https://github.com/joelgrus/data-science-from-scratch/blob/master/links.md) from the book.
 
-And, by popular demand, I made an index of functions defined in the book, by chapter and page number. 
+And, by popular demand, I made an index of functions defined in the book, by chapter and page number.
 The data is in a [spreadsheet](https://docs.google.com/spreadsheets/d/1mjGp94ehfxWOEaAFJsPiHqIeOioPH1vN1PdOE6v1az8/edit?usp=sharing), or I also made a toy (experimental) [searchable webapp](http://joelgrus.com/experiments/function-index/).
 
+## Installations
+
+```
+pip install -r requirements.txt
+```
+
 ## Table of Contents
 
 1. Introduction

code-python3/getting_data.py

@@ -157,7 +157,7 @@ def process(date, symbol, price):
 
     print("tab delimited stock prices:")
 
-    with open('tab_delimited_stock_prices.txt', 'r', encoding='utf8',newline='') as f:
+    with open('../data/tab_delimited_stock_prices.txt', 'r', encoding='utf8',newline='') as f:
         reader = csv.reader(f, delimiter='\t')
         # reader = csv.reader(codecs.iterdecode(f, 'utf-8'), delimiter='\t')
         for row in reader:
@@ -170,7 +170,7 @@ def process(date, symbol, price):
 
     print("colon delimited stock prices:")
 
-    with open('colon_delimited_stock_prices.txt', 'r', encoding='utf8',newline='') as f:
+    with open('../data/colon_delimited_stock_prices.txt', 'r', encoding='utf8',newline='') as f:
         reader = csv.DictReader(f, delimiter=':')
         # reader = csv.DictReader(codecs.iterdecode(f, 'utf-8'), delimiter=':')
         for row in reader:
@@ -181,11 +181,11 @@ def process(date, symbol, price):
 
     print()
 
-    print("writing out comma_delimited_stock_prices.txt")
+    print("writing out ../data/comma_delimited_stock_prices.txt")
 
     today_prices = { 'AAPL' : 90.91, 'MSFT' : 41.68, 'FB' : 64.5 }
 
-    with open('comma_delimited_stock_prices.txt','w', encoding='utf8',newline='') as f:
+    with open('../data/comma_delimited_stock_prices.txt','w', encoding='utf8',newline='') as f:
         writer = csv.writer(f, delimiter=',')
         for stock, price in today_prices.items():
             writer.writerow([stock, price])

code-python3/plot_state_borders.py

@@ -6,7 +6,7 @@
 
 lat_long_regex = r"<point lat=\"(.*)\" lng=\"(.*)\""
 
-with open("states.txt", "r") as f:
+with open("../data/states.txt", "r") as f:
     lines = [line for line in f]
 
 for line in lines:

code-python3/working_with_data.py

@@ -395,7 +395,7 @@ def transform(X, components):
 
     data = []
 
-    with open("comma_delimited_stock_prices.csv", "r", encoding='utf8', newline='') as f:
+    with open("../data/comma_delimited_stock_prices.csv", "r", encoding='utf8', newline='') as f:
         reader = csv.reader(f)
         for line in parse_rows_with(reader, [dateutil.parser.parse, None, float]):
             data.append(line)
@@ -405,7 +405,7 @@ def transform(X, components):
             print(row)
 
     print("stocks")
-    with open("stocks.txt", "r", encoding='utf8', newline='') as f:
+    with open("../data/stocks.txt", "r", encoding='utf8', newline='') as f:
         reader = csv.DictReader(f, delimiter="\t")
         data = [parse_dict(row, { 'date' : dateutil.parser.parse,
                                   'closing_price' : float })

code/getting_data.py

@@ -158,7 +158,7 @@ def process(date, symbol, price):
 
     print "tab delimited stock prices:"
 
-    with open('tab_delimited_stock_prices.txt', 'rb') as f:
+    with open('../data/tab_delimited_stock_prices.txt', 'rb') as f:
         reader = csv.reader(f, delimiter='\t')
         for row in reader:
             date = row[0]
@@ -170,7 +170,7 @@ def process(date, symbol, price):
 
     print "colon delimited stock prices:"
 
-    with open('colon_delimited_stock_prices.txt', 'rb') as f:
+    with open('../data/colon_delimited_stock_prices.txt', 'rb') as f:
         reader = csv.DictReader(f, delimiter=':')
         for row in reader:
             date = row["date"]
@@ -180,11 +180,11 @@ def process(date, symbol, price):
 
     print
 
-    print "writing out comma_delimited_stock_prices.txt"
+    print "writing out ../data/comma_delimited_stock_prices.txt"
 
     today_prices = { 'AAPL' : 90.91, 'MSFT' : 41.68, 'FB' : 64.5 }
 
-    with open('comma_delimited_stock_prices.txt','wb') as f:
+    with open('../data/comma_delimited_stock_prices.txt','wb') as f:
         writer = csv.writer(f, delimiter=',')
         for stock, price in today_prices.items():
             writer.writerow([stock, price])

code/plot_state_borders.py

@@ -5,7 +5,7 @@
 
 lat_long_regex = r"<point lat=\"(.*)\" lng=\"(.*)\""
 
-with open("states.txt", "r") as f:
+with open("../data/states.txt", "r") as f:
     lines = [line for line in f]
 
 for line in lines: