Python manipulation

py/clustering.py

@@ -0,0 +1,23 @@
+from util import getQuery
+import pandas as p
+import matplotlib.pyplot as plt
+import seaborn as sns
+
+
+query = """
+SELECT icp_id, read_date + CONCAT(period / 2, ':', period %% 2 * 30, ':00')::time AS read_time,
+    kwh_tot
+FROM public.coup_tall_april WHERE icp_id LIKE (%s) ORDER BY icp_id, read_time;
+"""
+
+qparams = ['%%1117']
+
+df = getQuery(query, qparams)
+
+print(df.info())
+
+sns.set()
+
+sns.scatterplot(x = 'read_time', y = 'kwh_tot', hue = 'icp_id', style = 'icp_id', data = df)
+
+plt.show()

py/util.py

@@ -0,0 +1,56 @@
+import psycopg2 as pg
+from configparser import ConfigParser
+import pandas.io.sql as psql
+
+def config(filename='database.ini', section='postgresql'):
+    """Config parser from http://www.postgresqltutorial.com/postgresql-python/connect/"""
+    # create a parser
+    parser = ConfigParser()
+    # read config file
+    parser.read(filename)
+ 
+    # get section, default to postgresql
+    db = {}
+    if parser.has_section(section):
+        params = parser.items(section)
+        for param in params:
+            db[param[0]] = param[1]
+    else:
+        raise Exception('Section {0} not found in the {1} file'.format(section, filename))
+ 
+    return db
+
+def getQuery(query, qparams = []):
+    """
+    Get single query
+    """
+    conn = False
+
+    try:
+        params = config()
+
+        print("Connecting to database")
+
+        conn = pg.connect(**params)
+        cur = conn.cursor()
+
+        # Get table
+        dataframe = psql.read_sql(query, conn, params = qparams)
+
+        cur.close()
+
+        return dataframe
+
+    except (Exception, pg.DatabaseError) as error:
+        print(error)
+        return None
+
+    finally:
+        if conn is not False:
+            conn.close()
+            print('Database connection closed')
+
+if __name__ == "__main__":
+    dv = getQuery('SELECT version()').version[0]
+    print('PostgreSQL database version:')
+    print(dv)