Keep files up to date

Author: Tania Allard

.gitignore/.gitignore

@@ -1,6 +1,5 @@
 # Byte-compiled / optimized / DLL files
 __pycache__
-__pycache__
 *.py[cod]
 *$py.class
 
@@ -104,3 +103,6 @@ ENV/
 
 /data
 */.DS_Store
+
+# pytest
+.pytest_cache/

04_Testing.ipynb

@@ -24,11 +24,11 @@
    "metadata": {},
    "source": [
     "There are various approaches to tests software:\n",
-    "- Assertions: 🦄 == 🦄\n",
-    "- Exceptions: within the code serve as ⚠️\n",
-    "- Unit tests: investigate the behaviour of units of code (e.g functions)\n",
-    "- Regression tests: defends against 🐛\n",
-    "- Integration tests: ⚙️ checks that the pieces work together as expected"
+    "- **Assertions**: 🦄 == 🦄\n",
+    "- **Exceptions**: within the code serve as warnings ⚠️\n",
+    "- **Unit tests**: investigate the behaviour of units of code (e.g functions)\n",
+    "- **Regression tests**: defends against 🐛\n",
+    "- **Integration tests**: ⚙️ checks that the pieces work together as expected"
    ]
   },
   {
@@ -50,16 +50,12 @@
     "And we will modify this function too:\n",
     "```python\n",
     "def get_country(filename, country):\n",
-    "   \n",
-    "\n",
     "    # Load table\n",
     "    wine = pd.read_csv(filename)\n",
     "\n",
     "    # Use the country name to subset data\n",
     "    subset_country = wine[wine['country'] == country ].copy()\n",
     "\n",
-    "    # Subset the\n",
-    "\n",
     "    # Constructing the fname\n",
     "    today = datetime.datetime.today().strftime('%Y-%m-%d')\n",
     "    fname = f'data/processed/{today}-winemag_{country}.csv'\n",
@@ -76,8 +72,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now we need to create out testing scripts. \n",
-    "Some resources:\n",
+    "Now we are going to create our testing suite. \n",
+    "To run the tests we are going to use **pytest**.\n",
+    "You can find more information in the following resources:\n",
     "- Pytest usage examples can be found [here](http://doc.pytest.org/en/latest/usage.html)\n",
     "- Rules for [test discovery](http://doc.pytest.org/en/latest/goodpractices.html)\n",
     "\n",
@@ -86,7 +83,7 @@
     "$ touch tests/__init__.py\n",
     "$ touch test_03_country_subset.py\n",
     "```\n",
-    "Your test scrips should start with `test`"
+    "⭐ Your test scripts name must start with: `test`"
    ]
   },
   {

solutions/01_subset-data-GBP.py

@@ -27,7 +27,7 @@ def process_data_GBP(filename):
 
     Returns:
     -----
-    data_path: st
+    fname: st
         Path to the created data set
     """
 

solutions/03_country-subset-forTest.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python
+
+
+import sys
+import datetime
+
+import pandas as pd
+
+
+def get_country(filename, country):
+    """
+    Do a simple analysis per country
+    Args:
+    -----
+    filename: str
+        Path to the filename containing the wine data
+    country: str
+        Country to be used to subset
+
+    Returns:
+    -----
+    data_path: st
+        Path to the created data set
+    """
+
+    # Load table
+    wine = pd.read_csv(filename)
+
+    # Use the country name to subset data
+    subset_country = wine[wine['country'] == country ].copy()
+    subset_country.reset_index(drop=True, inplace=True)
+
+    # Constructing the fname
+    today = datetime.datetime.today().strftime('%Y-%m-%d')
+    fname = f'data/processed/{today}-winemag_{country}.csv'
+
+    # Saving the csv
+    subset_country.to_csv(fname, index =False)
+    print(fname)  # print the fname from here
+
+    return(subset_country)  #returns the data frame
+
+def get_mean_price(filename):
+    wine = pd.read_csv(filename)
+    mean_price = wine['price'].mean()
+    return round(mean_price, 4)
+
+if __name__ == '__main__':
+    filename = sys.argv[1]
+    country = sys.argv[2]
+    print(f'Subsetting: {filename}')
+    print(f'Country searched: {country}')
+
+    print(get_country(filename, country))

solutions/03_country-subset.py

@@ -11,14 +11,15 @@ def get_country(filename, country):
     """
     Do a simple analysis per country
     Args:
+    -----
     filename: str
         Path to the filename containing the wine data
     country: str
         Country to be used to subset
 
     Returns:
-
-    data_path: st
+    -----
+    fname: st
         Path to the created data set
     """
 
@@ -37,14 +38,9 @@ def get_country(filename, country):
 
     # Saving the csv
     subset_country.to_csv(fname, index =False)
-    print(fname)  # print the fname from here
-
-    return(subset_country)  #returns the data frame
+    
+    return(fname)
 
-def get_mean_price(filename):
-    wine = pd.read_csv(filename)
-    mean_price = wine['price'].mean()
-    return round(mean_price, 4)
 
 if __name__ == '__main__':
     filename = sys.argv[1]

solutions/test01_subset-data-GBP.py

@@ -5,13 +5,14 @@
 
 country = importlib.import_module('.data.03_country-subset', 'src')
 
-interim_data = "data/interim/2018-04-30-winemag_priceGBP.csv"
-processed_data = "data/processed/2018-05-03-winemag_Chile.csv"
+interim_data = "data/interim/2018-05-09-winemag_priceGBP.csv"
+processed_data = "data/processed/2018-05-09-winemag_Chile.csv"
+
 
 def test_get_mean_price():
     mean_price = country.get_mean_price(processed_data)
     assert mean_price == 20.7865
-    npt.assert_allclose(country.get_mean_price(processed_data) , 20.787, rtol = 0.01)
+    npt.assert_allclose(country.get_mean_price(processed_data), 20.787, rtol = 0.01)
 
 def test_get_country():
     df = country.get_country(interim_data, 'Chile')