Assignments

Pipfile

@@ -0,0 +1,17 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+python-dotenv = "*"
+psycopg2-binary = "*"
+pandas = "*"
+sqlalchemy = "*"
+pymongo = "*"
+dnspython = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.7"

app/chinook_queries.py

@@ -0,0 +1,20 @@
+import os
+import sqlite3
+
+# construct a path to wherever your database exists
+#DB_FILEPATH = "chinook.db"
+DB_FILEPATH = os.path.join(os.path.dirname(__file__), "..", "data", "chinook.db")
+
+connection = sqlite3.connect(DB_FILEPATH)
+print("CONNECTION:", connection)
+
+cursor = connection.cursor()
+print("CURSOR", cursor)
+
+query = "SELECT * FROM customers"
+
+#result = cursor.execute(query)
+#print("RESULT", result) #> returns cursor object w/o results (need to fetch the results)
+
+result2 = cursor.execute(query).fetchall()
+print("RESULT 2", result2)

module1-introduction-to-sql/buddymove_holidayiq_queries.py

@@ -0,0 +1,22 @@
+import os
+import sqlite3
+import pandas as pd 
+
+FILEPATH = os.path.join(os.path.dirname(__file__), 'buddymove_holidayiq.csv')
+DB_FILEPATH = os.path.join(os.path.dirname(__file__), 'buddymove_holidayiq.sqlite3')
+
+connection = sqlite3.connect(DB_FILEPATH)
+cursor = connection.cursor()
+
+# creat dataframe
+df = pd.read_csv(FILEPATH)
+
+df.to_sql('review', connection, if_exists='replace')
+
+query = "SELECT COUNT('index') FROM review"
+result = cursor.execute(query).fetchall()
+print(f'Total number of rows is {result[0][0]}')
+
+query = "SELECT COUNT('index') FROM review WHERE Nature>=100 and Shopping>=100"
+result = cursor.execute(query).fetchall()
+print(f'Number of people who reveiwed more that 100 Shopping and Nature: {result[0][0]}')

module1-introduction-to-sql/rpg_queries.py

@@ -0,0 +1,62 @@
+import os
+import sqlite3
+
+DB_FILEPATE = os.path.join(os.path.dirname(__file__), 'rpg_db.sqlite3')
+
+connection = sqlite3.connect(DB_FILEPATE)
+
+cursor = connection.cursor()
+
+# How many total Characters
+query = 'SELECT count(DISTINCT character_id) FROM charactercreator_character'
+result = cursor.execute(query).fetchall()
+print('Number of total characters:', result[0][0], '\n')
+
+# How many of each specific subclass?
+clerics = 'SELECT count(DISTINCT character_ptr_id) as Number_of_Clerics FROM charactercreator_cleric'
+fighters = 'SELECT count(DISTINCT character_ptr_id) as Number_of_Fighters FROM charactercreator_fighter'
+mages = 'SELECT count(DISTINCT character_ptr_id) as Number_of_Mages FROM charactercreator_mage'
+necromancers = 'SELECT count(DISTINCT mage_ptr_id) as Number_of_Necromancers FROM charactercreator_necromancer'
+thieves = 'SELECT count(DISTINCT character_ptr_id) as Number_of_Theives FROM charactercreator_thief'
+subclass = [clerics, fighters, mages, necromancers, thieves]
+for x in subclass:
+    result = cursor.execute(x).fetchall()
+    print('Number of clerics, fighter, mages, necromancers, and thieves, respectively:', result[0][0])
+print('\n')
+
+# how many total items?
+query = 'SELECT count(DISTINCT item_id) FROM armory_item'
+item_result = cursor.execute(query).fetchall()
+print(f'Total number of items: {item_result[0][0]}', '\n')
+
+# How many of the items are wepons? How many are not?
+query = 'SELECT count(DISTINCT item_ptr_id) FROM armory_weapon'
+weapon_result = cursor.execute(query).fetchall()
+num = weapon_result[0][0]
+print(f'Number of weapons: {num}, Number of not weapons: {item_result[0][0] - num}', '\n')
+
+# How many items does each character have? (first 20)
+query = 'SELECT charactercreator_character.name, COUNT(charactercreator_character_inventory.item_id) as item_count FROM charactercreator_character_inventory JOIN charactercreator_character ON charactercreator_character_inventory.character_id = charactercreator_character.character_id GROUP BY name ORDER BY item_count DESC LIMIT 20'
+result = cursor.execute(query).fetchall()
+print('Top 20 characters with the most items:')
+for i in range(0, len(result)):
+    print(f'{i+1}: {result[i][0]} has {result[i][1]} items')
+print('\n')
+
+# How many weapons does each character have? (first 20)
+query = 'SELECT charactercreator_character.name, COUNT(charactercreator_character_inventory.item_id) as item_count FROM charactercreator_character_inventory JOIN charactercreator_character on charactercreator_character_inventory.character_id = charactercreator_character.character_id JOIN armory_weapon ON charactercreator_character_inventory.item_id = armory_weapon.item_ptr_id GROUP BY name ORDER BY item_count DESC LIMIT 20'
+result = cursor.execute(query).fetchall()
+print('Top 20 characters with the most weapons:')
+for i in range(0, len(result)):
+    print(f'{i+1}: {result[i][0]} has {result[i][1]} weapons')
+print('\n')
+
+# On average, how many items does each Character have?
+query = 'SELECT avg(item_count) FROM ( SELECT charactercreator_character.name, COUNT(charactercreator_character_inventory.item_id) as item_count FROM charactercreator_character_inventory LEFT JOIN charactercreator_character ON charactercreator_character_inventory.character_id = charactercreator_character.character_id GROUP BY name ORDER BY item_count DESC )subq'
+result = cursor.execute(query).fetchall()
+print(f'Average number of items per character is {result[0][0]:.3f}')
+
+# On average, how many Weapons does each character have?
+query = 'SELECT avg(item_count) FROM (SELECT charactercreator_character.name, COUNT(charactercreator_character_inventory.item_id) as item_count FROM charactercreator_character_inventory LEFT JOIN charactercreator_character on charactercreator_character_inventory.character_id = charactercreator_character.character_id JOIN armory_weapon ON charactercreator_character_inventory.item_id = armory_weapon.item_ptr_id GROUP BY name)subq'
+result = cursor.execute(query).fetchall()
+print(f'Average number of weapons per character is {result[0][0]:.3f}')

module2-sql-for-analysis/elephant_queries.py

@@ -0,0 +1,53 @@
+import psycopg2
+from psycopg2.extras import execute_values
+import os
+from dotenv import load_dotenv
+import json
+
+load_dotenv()
+DB_NAME = os.getenv('DB_NAME')
+DB_USER = os.getenv('DB_USER')
+DB_PASSWORD = os.getenv('DB_PASSWORD')
+DB_HOST = os.getenv('DB_HOST')
+
+### Connect to ElephantSQL-hosted PostgreSQL
+conn = psycopg2.connect(dbname=DB_NAME, user=DB_USER,
+                        password=DB_PASSWORD, host=DB_HOST)
+### A "cursor", a structure to iterate over db records to perform queries
+cur = conn.cursor()
+### An example query
+cur.execute('SELECT * from test_table;')
+### Note - nothing happened yet! We need to actually *fetch* from the cursor
+result = cur.fetchall()
+print(result)
+
+print("---------------")
+query = f'''
+CREATE TABLE IF NOT EXISTS test_table2 (
+    id SERIAL PRIMARY KEY,
+    name varchar(40) NOT NULL,
+    data JSONB
+);
+'''
+print('SQL:', query)
+cur.execute(query)
+
+my_dict = {'a':1, 'b':['dog','cat',42], 'c':'true'}
+
+insertion_query = 'INSERT INTO test_table2 (name, data) VALUES %s'
+execute_values( cur, insertion_query, [
+    ('A rowwwww', 'null'),
+    ('Another row with JSON', json.dumps(my_dict)),
+    ('Third row', '3')
+])
+
+
+
+# cur.execute(insertion_query, ('A rowwwwww', 'null'))
+
+# cur.execute(insertion_query, ('Another row, with JSONNNNN', json.dumps(my_dict)))
+
+conn.commit()
+
+cur.close()
+conn.close()

module2-sql-for-analysis/titanic.py

@@ -0,0 +1,37 @@
+import psycopg2
+from psycopg2.extras import execute_values
+import os
+from dotenv import load_dotenv
+import json
+import pandas as pd
+import sqlalchemy
+
+load_dotenv()
+DB_NAME = os.getenv('DB_NAME')
+DB_USER = os.getenv('DB_USER')
+DB_PASSWORD = os.getenv('DB_PASSWORD')
+DB_HOST = os.getenv('DB_HOST')
+DB_URL = os.getenv('DB_URL')
+
+
+conn = psycopg2.connect(dbname=DB_NAME, user=DB_USER,
+                        password=DB_PASSWORD, host=DB_HOST)
+
+cur = conn.cursor()
+
+# create the dataframe
+path = os.path.join(os.path.dirname(__file__), 'titanic.csv')
+df = pd.read_csv(path)
+
+# creat table in database
+engine = sqlalchemy.create_engine(DB_URL)
+
+df.to_sql('titanic', con=engine, index=True, if_exists='replace')
+
+
+
+
+
+conn.commit()
+cur.close()
+conn.close()

module2-sql-for-analysis/titanic_queries.py

@@ -0,0 +1,26 @@
+import psycopg2
+import os
+from dotenv import load_dotenv
+import json
+
+load_dotenv()
+DB_NAME = os.getenv('DB_NAME')
+DB_USER = os.getenv('DB_USER')
+DB_PASSWORD = os.getenv('DB_PASSWORD')
+DB_HOST = os.getenv('DB_HOST')
+
+
+conn = psycopg2.connect(dbname=DB_NAME, user=DB_USER,
+                        password=DB_PASSWORD, host=DB_HOST)
+
+cur = conn.cursor()
+
+query = 'SELECT"Pclass", AVG("Age") FROM titanic GROUP BY"Pclass"'
+cur.execute(query)
+result = cur.fetchall()
+print(result)
+
+query = 'SELECT"Pclass", AVG("Fare") FROM titanic GROUP BY"Pclass"'
+cur.execute(query)
+result = cur.fetchall()
+print(result)

module3-nosql-and-document-oriented-databases/insert_rpg.py

@@ -0,0 +1,57 @@
+'''
+I think that relational databases are easier to work with. The biggest reason is because
+it makes it a lot easier to follow visually. MongoDB was easier to use because the rules
+seem to be a lot less strict on creating and inserting data. But I can also see that being a problem
+too, so it's a little bit of a double egded sword.
+'''
+
+import os
+import sqlite3
+import pymongo
+from dotenv import load_dotenv
+
+DB_FILEPATE = os.path.join(os.path.dirname(__file__), '..', 'module1-introduction-to-sql', 'rpg_db.sqlite3')
+
+connection = sqlite3.connect(DB_FILEPATE)
+
+connection.row_factory = sqlite3.Row
+cursor = connection.cursor()
+
+#make dictionaries for each row in charactercreator_character
+query = 'SELECT * FROM charactercreator_character'
+cursor.execute(query)
+result = cursor.fetchall()
+
+character_rows = [dict(row) for row in result]
+
+# make dict for each row in armory item
+query = 'SELECT * FROM armory_item'
+cursor.execute(query)
+result = cursor.fetchall()
+item_rows = [dict(row) for row in result]
+
+
+
+
+load_dotenv()
+
+DB_USER = os.getenv("MONGO_USER", default="OOPS")
+DB_PASSWORD = os.getenv("MONGO_PASSWORD", default="OOPS")
+CLUSTER_NAME = os.getenv("MONGO_CLUSTER_NAME", default="OOPS")
+
+connection_uri = f"mongodb+srv://{DB_USER}:{DB_PASSWORD}@{CLUSTER_NAME}.mongodb.net/test?retryWrites=true&w=majority"
+
+client = pymongo.MongoClient(connection_uri)
+
+db = client.Module3_db 
+
+# insert characters into db
+collection1 = db.characters 
+collection1.insert_many(character_rows)
+
+# insert items into db
+collection2 = db.items
+collection2.insert_many(item_rows)
+
+
+

module3-nosql-and-document-oriented-databases/mongo_queries.py

@@ -0,0 +1,38 @@
+import pymongo
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+DB_USER = os.getenv("MONGO_USER", default="OOPS")
+DB_PASSWORD = os.getenv("MONGO_PASSWORD", default="OOPS")
+CLUSTER_NAME = os.getenv("MONGO_CLUSTER_NAME", default="OOPS")
+
+connection_uri = f"mongodb+srv://{DB_USER}:{DB_PASSWORD}@{CLUSTER_NAME}.mongodb.net/test?retryWrites=true&w=majority"
+print("----------------")
+print("URI:", connection_uri)
+
+client = pymongo.MongoClient(connection_uri)
+print("----------------")
+print("CLIENT:", type(client), client)
+
+db = client.Module3_db # "test_database" or whatever you want to call it
+print("----------------")
+print("DB:", type(db), db)
+
+collection = db.pokemon # "pokemon_test" or whatever you want to call it
+print("----------------")
+print("COLLECTION:", type(collection), collection)
+
+print("----------------")
+print("COLLECTIONS:")
+print(db.list_collection_names())
+
+collection.insert_one({
+    "name": "Pikachu",
+    "level": 30,
+    "exp": 76000000000,
+    "hp": 400,
+})
+print("DOCS:", collection.count_documents({}))
+print(collection.count_documents({"name": "Pikachu"}))