# Size off the data chunk
size = 100000
##### Run Program
# Wait for the MySQL server to start
containerWait()
try:
# Connect to MySQL and get cursor
db_mysql, cur1 = connectMySQL(buffered=True)
# Check timestamps
if managementCompare('last_location_insert',
'last_predict_clusters',
cur=cur1,
db_mysql=db_mysql) or managementCompare(
'last_kmeans_model',
'last_predict_clusters',
cur=cur1,
db_mysql=db_mysql):
# Get second cursor
cur2 = db_mysql.cursor()
# Load the kmeans model
kmeanModel = pickle.load(open(path_model, 'rb'))
##### Get All Datapoints Tp Predict Clusters
# Select statement
# Path for the plot
path_model = 'build/KMeans_Model.p'
##### Run Program
# Wait for the MySQL server to start
containerWait()
try:
# Connect to MySQL and get cursor
db_mysql, cur = connectMySQL()
# Check timestamps
if managementCompare('last_predict_clusters',
'last_cluster_table',
cur=cur,
db_mysql=db_mysql):
# Load the kmeans model
kmeanModel = pickle.load(open(path_model, 'rb'))
# Get the centers for the clusters
kmeanCenters = kmeanModel.cluster_centers_
##### Map Clusters To Cities
# Clusters to city names
dict_cities = mapClustersToCities(kmeanCenters)
# Create a dataframe for the cities
df_cities = pd.DataFrame.from_dict(dict_cities, orient='index')
# Chunk size for input to database
size = 100000
##### Run Program
# Wait for the MySQL server to start
containerWait()
try:
# Connect to MySQL and get cursor
db_mysql, cur = connectMySQL()
# Check timestamps
if managementCompare('last_cluster_table',
'last_rides_table',
cur=cur,
db_mysql=db_mysql):
##### Get The Point And City Dataframes
# SQL query
sql_query = 'SHOW columns FROM city_clusters'
# Get column names
cur.execute(sql_query)
columns = [i[0] for i in cur.fetchall()]
# SQL query
sql_query = 'SELECT * FROM city_clusters'
# Get dataframe
# Wait for the MySQL server to start
containerWait()
try:
# Connect to ZODB
root = connectZEO()
# Connect to MySQL and get cursor
db_mysql, cur = connectMySQL()
# Check timestamps
if managementCompare('last_enrich_cluster_table', 'last_osm_download', cur=cur, db_mysql=db_mysql):
##### Iterate Over All Cities And Download OSM-Graph
# SQL query
sql_query = 'SELECT cluster_id FROM city_clusters WHERE city_analyse=1'
# Execute the query
cur.execute(sql_query)
cluster_ids = cur.fetchall()
# Iterate over all cities
for cluster_id in cluster_ids:
# Extract the data