import pandas as pd

print("1=================")
dict = {
    'name': ['Jan', 'Adam'],
    'surname': ['Kowalski', 'Nowak'],
    'age': [25, 43]
}
print(dict)
data_frame = pd.DataFrame(dict)
print(data_frame)

print("2=================")

import numpy as np

array = np.array([1,2,3,4,5])
print(array)
data_frame = pd.DataFrame(array)
print(data_frame)

print("3=================")

dict = {
    'name': ['Jan', 'Adam'],
    'surname': ['Kowalski', 'Nowak'],
    'age': [25, 43]
}
data_frame = pd.DataFrame(dict)
data_frame = data_frame.rename(index=str, columns={'name': 'first name', 'surname': 'last name'})
print(data_frame)

print("4=================")

numbers = {
    'numbers': [1,3,5,7,9,3]
}
data_frame = pd.DataFrame(numbers)
print(data_frame)
print(f'mean: {data_frame["numbers"].mean()}')
print(f'median: {data_frame["numbers"].median()}')
print(f'mode: {data_frame["numbers"].mode()}')

print("5=================")

dict = {
    'col1': ['C1', 'C1', 'C2', 'C2', 'C2', 'C3', 'C2'],
    'col2': [1,2,3,3,4,6,5]
}
data_frame = pd.DataFrame(dict)
print(data_frame)
print(data_frame.groupby('col1')['col2'].apply(list))

print("6=================")

dict = {
    'name': ['Jan', 'Adam'],
    'surname': ['Kowalski', 'Nowak'],
    'age': [25, 43]
}
data_frame = pd.DataFrame(dict)
data_frame = data_frame.drop('surname', axis=1)
print(data_frame)

print("7=================")

dict = {
    'col1': ['C1', 'C1', 'C2', 'C2', 'C2', 'C3', 'C2'],
    'col2': [1,2,np.inf,3,-np.inf,np.inf,5]
}
data_frame = pd.DataFrame(dict)
print(data_frame)
data_frame = data_frame[(data_frame.col2 != np.inf) & (data_frame.col2 != -np.inf)]
print(data_frame)

print("8=================")

data_frame = pd.DataFrame(np.random.randn(5, 3), columns=['col1', 'col2', 'col3'])
print(data_frame)
print(f'column 1: {data_frame.col1.idxmax()}')
print(f'column 2: {data_frame.col2.idxmax()}')
print(f'column 2: {data_frame.col3.idxmax()}')

print("9=================")

data_frame = pd.DataFrame({'x': [1, 2, 3, 4], 'y': [4, 5, 6, 7]})
print(data_frame)
print(data_frame[data_frame.columns[0]])

print("10=================")

data_frame = pd.read_csv('./Orange.csv')
print(data_frame)
print(data_frame.describe())

print("11=================")

import matplotlib.pyplot as plt
from sqlalchemy import create_engine

data = pd.read_csv('./muscle.csv')
engine = create_engine('sqlite:///:memory:')
data.to_sql('data_table', engine)
print(pd.read_sql_query('SELECT * FROM data_table', engine))

data["Length"].plot.hist(grid=True, bins=20, rwidth=0.9,
                          color="lightblue")
plt.title('Values of data[Length]')
plt.xlabel('Frequency')
plt.ylabel('Count')
plt.grid(axis='y', alpha=0.75)

plt.show()