# Learning pandas in about 10 minutes

# https://pandas.pydata.org/pandas-docs/stable/10min.html

# CNA 330

# Mustafa Musa, ammusa@student.rtc.edu

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

s = pd.Series([1, 3, 5, np.nan, 6, 8])

print(s)

dates = pd.date_range('20130101', periods=6)

print(dates)

df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))

print(df)

df2 = pd.DataFrame({'A': 1.,

'F': 'foo'})

print(df2)

print(df2.dtypes)

print(df.head())

print(df.tail(3))

print(df.index)

print(df.columns)

print(df.values)

print(df.describe())

print(df.T)

print(df.sort_index(axis=1, ascending=False))

print(df.sort_values(by='B'))

print(df['A'])

print(df[0:3])

print(df['20130101':'20130104'])

print(df.loc[dates[0]])

print(df.loc[:, ['A', 'B']])

print(df.loc['20130102':'20130104', ['A', 'B']])

print(df.loc['20130102', ['A', 'B']])

print(df.loc[dates[0], 'A'])

print(df.at[dates[0], 'A'])

print(df.iloc[3])

print(df.iloc[3:5, 0:2])

print(df.iloc[[1, 2, 4], [0, 2]])

print(df.iloc[1:3, :])

print(df.iloc[:, 1:3])

print(df.iloc[1, 1])

print(df.iat[1, 1])

print(df[df.A > 0])

print(df[df > 0])

df2 = df.copy()

df2['E'] = ['one', 'one', 'two', 'three', 'four', 'three']

print(df2)

print(df2[df2['E'].isin(['two','four'])])

s1 = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range('20130102', periods=6))

print(s1)

df['F'] = s1

df.at[dates[0], 'A'] = 0

df.iat[0, 1] = 0

df.loc[:, 'D'] = np.array([5] * len(df))

print(df)

df2 = df.copy()

df2[df2 > 0] = -df2

print(df2)

df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])

df1.loc[dates[0]:dates[1],'E'] = 1

print(df1)

df1.dropna(how='any')

df1.fillna(value=5)

pd.isna(df1)

df.mean()

df.mean(1)

s = pd.Series([1, 3, 5, np.nan, 6, 8], index=dates).shift(2)

print(s)

df.sub(s, axis='index')

df.apply(np.cumsum)

df.apply(lambda x: x.max() - x.min())

s = pd.Series(np.random.randint(0, 7, size=10))

print(s)

s.value_counts()

s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])

s.str.lower()

df = pd.DataFrame(np.random.randn(10, 4))

print(df)

pieces = [df[:3], df[3:7], df[7:]]

pd.concat(pieces)

left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})

right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})

print(left)

print(right)

pd.merge(left, right, on='key')

left = pd.DataFrame({'key': ['foo', 'bar'], 'lval': [1, 2]})

right = pd.DataFrame({'key': ['foo', 'bar'], 'rval': [4, 5]})

print(left)

print(right)

pd.merge(left, right, on='key')

df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])

print(df)

s = df.iloc[3]

df.append(s, ignore_index=True)

df = pd.DataFrame({

})

print(df)

df.groupby('A').sum()

df.groupby(['A','B']).sum()

tuples = list(zip(*[['bar', 'bar', 'baz', 'baz', 'foo', 'foo', 'qux', 'qux'],

['one', 'two', 'one', 'two', 'one', 'two', 'one', 'two']]))

index = pd.MultiIndex.from_tuples(tuples, names=['first', 'second'])

df = pd.DataFrame(np.random.randn(8, 2), index=index, columns=['A', 'B'])

df2 = df[:4]

print(df2)

stacked = df2.stack()

print(stacked)

stacked.unstack()

stacked.unstack(1)

stacked.unstack(0)

df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3,

'E' : np.random.randn(12)})

print(df)

pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])

rng = pd.date_range('1/1/2012', periods=100, freq='S')

ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng)

ts.resample('5Min').sum()

rng = pd.date_range('3/6/2012 00:00', periods=5, freq='D')

ts = pd.Series(np.random.randn(len(rng)), rng)

print(ts)

ts_utc = ts.tz_localize('UTC')

print(ts_utc)

ts_utc.tz_convert('US/Eastern')

rng = pd.date_range('1/1/2012', periods=5, freq='M')

ts = pd.Series(np.random.randn(len(rng)), index=rng)

print(ts)

ps = ts.to_period()

print(ps)

ps.to_timestamp()

prng = pd.period_range('1990Q1', '2000Q4', freq='Q-NOV')

ts = pd.Series(np.random.randn(len(prng)), prng)

ts.index = (prng.asfreq('M', 'e') + 1).asfreq('H', 's') + 9

ts.head()

df = pd.DataFrame({"id": [1, 2, 3, 4, 5, 6], "raw_grade": ['a', 'b', 'b', 'a',

'a', 'e']})

df["grade"] = df["raw_grade"].astype("category")

print(df["grade"])

df["grade"].cat.categories = ["very good", "good", "very bad"]

df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium", "good", "very good"])

print(df["grade"])

df.sort_values(by="grade")

df.groupby("grade").size()

ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))

ts = ts.cumsum()

ts.plot()

df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,

columns=['A', 'B', 'C', 'D'])

df = df.cumsum()

plt.figure()

df.plot()

plt.legend(loc='best')

df.to_csv('foo.csv')

pd.read_csv('foo.csv')