Merge pull request #386 from IntelPython/new_sdc_examples

Refactored Examples. Old examples are moved under old_examples folder…

Author: samaid

examples/basic_workflow.py

@@ -0,0 +1,48 @@
+# *****************************************************************************
+# Copyright (c) 2019, Intel Corporation All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#     Redistributions of source code must retain the above copyright notice,
+#     this list of conditions and the following disclaimer.
+#
+#     Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+# *****************************************************************************
+
+import pandas as pd
+from numba import njit
+
+# Dataset for analysis
+FNAME = "employees.csv"
+
+
+# This function gets compiled by Numba*
+@njit
+def get_analyzed_data():
+    df = pd.read_csv(FNAME)
+    s_bonus = pd.Series(df['Bonus %'])
+    s_first_name = pd.Series(df['First Name'])
+    m = s_bonus.mean()
+    names = s_first_name.sort_values()
+    return m, names
+
+
+# Printing names and their average bonus percent
+mean_bonus, sorted_first_names = get_analyzed_data()
+print(sorted_first_names)
+print('Average Bonus %:', mean_bonus)

examples/basic_workflow_parallel.py

@@ -0,0 +1,48 @@
+# *****************************************************************************
+# Copyright (c) 2019, Intel Corporation All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#     Redistributions of source code must retain the above copyright notice,
+#     this list of conditions and the following disclaimer.
+#
+#     Redistributions in binary form must reproduce the above copyright notice,
+#     this list of conditions and the following disclaimer in the documentation
+#     and/or other materials provided with the distribution.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
+# THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+# EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+# *****************************************************************************
+
+import pandas as pd
+from numba import njit
+
+# Dataset for analysis
+FNAME = "employees.csv"
+
+
+# This function gets compiled by Numba* and multi-threaded
+@njit(parallel=True)
+def get_analyzed_data():
+    df = pd.read_csv(FNAME)
+    s_bonus = pd.Series(df['Bonus %'])
+    s_first_name = pd.Series(df['First Name'])
+    m = s_bonus.mean()
+    names = s_first_name.sort_values()
+    return m, names
+
+
+# Printing names and their average bonus percent
+mean_bonus, sorted_first_names = get_analyzed_data()
+print(sorted_first_names)
+print('Average Bonus %:', mean_bonus)

examples/employees.csv

@@ -0,0 +1,11 @@
+,Gender,First Name,Start Date,Last Login Time,Salary,Bonus %,Senior Management,Team
+0,Female,EMILY,2015-12-04,0 days 21:41:41.000000000,39582,1.306,,Business Development
+1,Male,NOAH,2011-02-02,0 days 00:04:19.000000000,124742,5.881,False,Client Services
+2,Male,ISAAC,1994-10-25,0 days 04:35:46.000000000,138462,14.995,True,Sales
+3,Male,,1998-12-24,0 days 18:35:33.000000000,60661,3.477,False,Business Development
+4,,CHRISTOPHER,2002-03-05,0 days 12:26:32.000000000,97764,15.65,False,
+5,Female,MIA,2005-01-20,0 days 17:47:44.000000000,42104,12.595,False,Product
+6,Female,OLIVIA,1994-07-13,0 days 00:43:25.000000000,46646,1.284,False,Client Services
+7,Male,ALEXANDER,2019-09-03,0 days 04:15:00.000000000,123807,17.849,True,Legal
+8,Male,JOSEPH,2008-09-15,0 days 01:16:05.000000000,139681,19.904,False,Engineering
+9,Male,JOSEPH,2009-06-11,0 days 20:27:06.000000000,71359,19.103,False,Client Services