R, Python 분석과 프로그래밍의 친구 (by R Friend)

  1. List Comprehension: [0 if i < 0 else i for i in a]

>>> import numpy as np

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> [0 if i < 0 else i for i in a]

[0, 0, 0, 0, 0, 0, 1, 2, 3, 4]

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

  2. Indexing: a[a < 0] = 0

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> a[a < 0] = 0

>>> a

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

  3. np.where() : np.where(a < 0, 0, a)

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> np.where(a < 0, 0, a)

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>>

>>> np.where(a < 0, 0, np.where(a > 2, 2, a))

array([0, 0, 0, 0, 0, 0, 1, 2, 2, 2])

  4. np.clip() : np.clip(a, 0, 4, out=a)

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> np.clip(a, 0, 4)

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> np.clip(a, 0, 4, out=a)

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

>>> a

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

>>> a = np.arange(-5, 5)

>>> a

array([-5, -4, -3, -2, -1,  0,  1,  2,  3,  4])

>>> a.clip(0)

array([0, 0, 0, 0, 0, 0, 1, 2, 3, 4])

(1) 3개의 그룹 변수, 4개의 연속형 변수를 가진 예제 DataFrame 만들기

import numpy as np

import pandas as pd

# making groups

group_1 = ['A', 'B']*20

group_2 = ['C', 'D', 'E', 'F']*10

group_3 = ['G', 'H', 'I', 'J', 'K', 'L', 'M', 'N']*5;

df = pd.DataFrame({'group_1': group_1, 

                   'group_2': group_2,

                   'group_3': group_3,

                   'col_1': np.random.randn(40), 

                   'col_2': np.random.randn(40), 

                   'col_3': np.random.randn(40), 

                   'col_4': np.random.randn(40)})

df.sort_values(by=['group_1', 'group_2', 'group_3'], axis=0)

  (2) 그룹별 두 개 변수 간 상관계수를 구하는 사용자 정의 함수

# a user-defined function of correlation coefficients with paired variables by groups

def corr_group(df, var_1, var_2, group_list):

    # correlaiton fuction with 2 variables

    corr_func = lambda g: g[var_1].corr(g[var_2])

    # GroupBy operator

    grouped = df.groupby(group_list)

    # calculate correlation coefficient by Group

    corr_coef_df = pd.DataFrame(grouped.apply(corr_func), columns=['corr_coef'])

    # add var_1, var_2 column names

    corr_coef_df['var1'] = var_1

    corr_coef_df['var2'] = var_2

    return corr_coef_df

  (3) 다수 그룹별 다수 변수 간 두개 씩 쌍을 이루어 상관계수 구하기

# blank DataFrame

corr_coef_df_all = pd.DataFrame()

# group by list

group_list = ['group_1', 'group_2', 'group_3']

# column lists for correlation matrix

col_list = ['col_1', 'col_2', 'col_3', 'col_4']

# get all cominations of col_list with length 2

from itertools import combinations

comb = combinations(col_list, 2)

# calculate correlation coefficients pair-wise

for var in list(comb):

    corr_tmp = corr_group(df, var[0], var[1], group_list)

    corr_coef_df_all = corr_coef_df_all.append(corr_tmp)

# result

corr_coef_df_all[['var1', 'var2', 'corr_coef']]

# import plotly standard

import plotly.plotly as py

import plotly.graph_objs as go

import plotly.figure_factory as ff

# Cufflinks wrapper on plotly

import cufflinks as cf

# Display all cell outputs

from IPython.core.interactiveshell import InteractiveShell

# plotly + cufflinks in offline mode

from plotly.offline import iplot

cf.go_offline()

# set the global theme

cf.set_config_file(world_readable=True, theme='pearl', offline=True)

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

# data loading

iris = sns.load_dataset('iris')

iris.shape

(150, 5) 

iris.head()

  (3) Plotly를 오프라인 Jupyter Notebook에서 사용한 히스토그램(histogram)

# Histogram with Frequency

iris['petal_length'].iplot(

    kind='hist', 

    bins=20, 

    xTitle='Petal Length(cm)', 

    linecolor='gray', 

    yTitle='Count', 

    title='Histogram of Petal Length')

# Histogram with Percentage

iris['petal_length'].iplot(

    kind='hist', 

    bins=20, 

    xTitle='Petal Length(cm)', 

    linecolor='gray', 

    histnorm='percent',

    yTitle='Percentage(%)', 

    title='Histogram of Petal Length in Percent')

  (4) Plotly를 오프라인 Jupyter Notebook에서 사용한 산점도 행렬(scatterplot matrix)

fig = ff.create_scatterplotmatrix(

    iris[['petal_width', 'petal_length', 'sepal_width', 'sepal_length']],

    height=800,

    width=800, 

    diag='histogram') # scatter, histogram, box

iplot(fig)

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [10, 8]

# data loading

flights = sns.load_dataset('flights')

flights.head()

  명령 프롬프트에서 'PlotNine' 라이브러리 설치하기

Microsoft Windows [Version 10.0.17134.523]

(c) 2018 Microsoft Corporation. All rights reserved.

C:\Users\admin>conda env list

# conda environments:

#

base                  *  C:\Users\admin\Anaconda3

py_v35                   C:\Users\admin\Anaconda3\envs\py_v35

py_v36                   C:\Users\admin\Anaconda3\envs\py_v36

C:\Users\admin>activate py_v36

(py_v36) C:\Users\admin>pip install plotnine

  (1) PlotNine 라이브러리를 사용하여 파이썬에서 R ggplot2 함수로 선 그래프 그리기

# line graph using R ggplot2 function in Python environment by plotnine library

from plotnine import *

fig = plt.figure()

ggplot(flights, aes(x='year', y='passengers', group='month', color='month')) \

    + geom_line() \

    + ggtitle('Time Series Graph of Flight')

  (2) PlotNine 라이브러리를 사용하여 파이썬에서 R ggplot2 함수로 히트맵 그리기

# heatmap using R ggplot2 function in Python environment by plotnine library

from plotnine import *

fig = plt.figure()

ggplot(flights, aes(x='year', y='month')) \

    + geom_tile(aes(fill='passengers')) \

    + scale_fill_gradientn(colors=['#9ebcda','#8c6bb1','#88419d','#6e016b']) \

    + ggtitle('Heatmap of Flights by plotnine')

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [10, 8]

flights = sns.load_dataset('flights')

flights.head()

df = flights.pivot('month', 'year', 'passengers')

df.head()

  (1) matplotlib을 이용한 히트맵 그리기 (Heatmap by matplotlib)

# heatmap by plt.pcolor()

plt.pcolor(df)

plt.xticks(np.arange(0.5, len(df.columns), 1), df.columns)

plt.yticks(np.arange(0.5, len(df.index), 1), df.index)

plt.title('Heatmap by plt.pcolor()', fontsize=20)

plt.xlabel('Year', fontsize=14)

plt.ylabel('Month', fontsize=14)

plt.colorbar()

plt.show()

  (2) seaborn을 이용한 히트맵 그리기 (Heatmap by seaborn)

# heatmap by seaborn

ax = sns.heatmap(df)

plt.title('Heatmap of Flight by seaborn', fontsize=20)

plt.show() 

# annotate each cell with the numeric value of integer format

sns.heatmap(df, annot=True, fmt='d')

plt.title('Annoteat cell with numeric value', fontsize=20)

plt.show()

# different colormap

sns.heatmap(df, cmap='RdYlGn_r')

plt.title('colormap of cmap=RdYlGn_r', fontsize=20)

plt.show()

# different colormap

sns.heatmap(df, cmap='YlGnBu') # 

plt.title('colormap of cmap=YlGnBu', fontsize=20)

plt.show()

# center the colormap at a specific value

sns.heatmap(df, center=df.loc['January', 1949])

plt.title('Center the colormap at Jan. 1949', fontsize=20)

plt.show()

  (3) pandas를 이용한 히트맵 그리기 (Heatmap by pandas)

# heatmap by pandas

df.style.background_gradient(cmap='summer')

import numpy as np

import pandas as pd

from statsmodels.graphics.mosaicplot import mosaic

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [12, 8]

# Getting Titanic dataset

url = "https://raw.github.com/mattdelhey/kaggle-titanic/master/Data/train.csv"

titanic = pd.read_csv(url)

titanic.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 11 columns):
survived    891 non-null int64
pclass      891 non-null int64
name        891 non-null object
sex         891 non-null object
age         714 non-null float64
sibsp       891 non-null int64
parch       891 non-null int64
ticket      891 non-null object
fare        891 non-null float64
cabin       204 non-null object
embarked    889 non-null object
dtypes: float64(2), int64(4), object(5)
memory usage: 76.6+ KB

titanic = titanic[['survived', 'pclass', 'sex']]

# make new variables of 'survived' and 'pclass' with the different class name

titanic["SURVIVE"] = titanic.survived.map({0: "DEAD", 1: "ALIVE"})

titanic["CLASS"] = titanic.pclass.map({1: "1ST", 2: "2ND", 3: "3RD"})

titanic["GENDER"] = titanic.sex.map({'male': 'MAN', 'female': "WOMAN"})

titanic.head()

from statsmodels.graphics.mosaicplot import mosaic

mosaic(titanic.sort_values('CLASS'), ['SURVIVE', 'CLASS'], 

      title='Mosaic Chart of Titanic Survivor')

plt.show()

mosaic(titanic, ['SURVIVE', 'GENDER'])

plt.title('Mosaic Chart of Titanic', fontsize=20)

plt.show()

mosaic(titanic.sort_values('CLASS'), ['CLASS', 'SURVIVE', 'GENDER'])

plt.title('Mosaic Chart of Titanic', fontsize=20)

plt.show()

mosaic(titanic.sort_values('CLASS'), ['CLASS', 'SURVIVE', 'GENDER'], 

      gap=0.02)

plt.title('Survivor of Titanic', fontsize=20)

plt.show()

  (Data form 1) Wide-form DataFrame

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [12, 8]

np.random.seed(123) # for reproducibility

index = pd.date_range("1 1 2010", 

                      periods=100, 

                      freq="m", 

                      name="Date")

data = np.random.randn(100, 4).cumsum(axis=0)

wide_df = pd.DataFrame(data, index, ['a', 'b', 'c', 'd'])

wide_df.shape

(100, 4)

wide_df.head()

  (Data form 2) Long-form DataFrame

# stack to reshape from wide to long

long = wide_df.stack()

long_df = pd.DataFrame(long).reset_index()

long_df.head()

# change column nane

long_df.columns = ['Date', 'Group', 'CumVal']

long_df.head()

long_df.shape

(400, 3)

# adding a 'Size' column based on 'Group'

long_df['Size'] = np.where(long_df['Group'] == 'a', 1, 

                           np.where(long_df['Group'] == 'b', 2, 

                                    np.where(long_df['Group'] == 'c', 3, 4)))

long_df.head(n=12)

  1. matplotlib으로 선 그래프 그리기 (Line Graph by matplotlib)

# Line Graph by matplotlib with wide-form DataFrame

plt.plot(wide_df.index, wide_df.a, marker='s', color='r')

plt.plot(wide_df.index, wide_df.b, marker='o', color='g')

plt.plot(wide_df.index, wide_df.c, marker='*', color='b')

plt.plot(wide_df.index, wide_df.d, marker='+', color='y')

plt.title('Line Graph w/ different markers and colors', fontsize=20) 

plt.ylabel('Cummulative Num', fontsize=14)

plt.xlabel('Date', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

# Line Graph by matplotlib with different line style and line width

plt.plot(wide_df.index, wide_df.a, linestyle='--', linewidth=1) # 'dashed'

plt.plot(wide_df.index, wide_df.b, linestyle='-', linewidth=2) # solid

plt.plot(wide_df.index, wide_df.c, linestyle=':', linewidth=3) # dotted

plt.plot(wide_df.index, wide_df.d, linestyle='-.', linewidth=4) # dashdotted

plt.title('Line Graph w/ different linestyles and linewidths', fontsize=20) 

plt.ylabel('Cummulative Num', fontsize=14)

plt.xlabel('Date', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

long_df.head(n=8)

# Line graph with long-form DataFrame

groups = ['a', 'b', 'c', 'd']

linewidths = [1, 2, 3, 4]

for group_name, size in zip(groups, linewidths):

    # subsetting

    long_df_sub = long_df[long_df['Group'] == group_name]

    # plotting

    plt.plot(long_df_sub.Date, long_df_sub.CumVal, linewidth=size)

plt.legend(['a', 'b', 'c', 'd'], fontsize=12, loc='best')

plt.show()

  2. seaborn으로 선 그래프 그리기 (Line Graph by seaborn)

# Line graph by seaborn

ax = sns.lineplot(data=wide_df)

plt.title('Line Graph w/ Wide-form DataFrame by seaborn', fontsize=20)

plt.ylabel('Cummulative Num', fontsize=14)

plt.xlabel('Date', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

# Line graph with long-form DataFrame

long_df.head(n=8)

ax = sns.lineplot(x='Date', 

                  y='CumVal', 

                  hue='Group',

                  size='Size',

                  data=long_df)

plt.title('Line Graph of different size w/ Long-form df by seaborn', fontsize=20)

plt.ylabel('Cummulative Num', fontsize=14)

plt.xlabel('Date', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

ax = sns.lineplot(x='Date', 

                  y='CumVal', 

                  #hue='Group',

                  style='Size',

                  data=long_df)

plt.title('Line Graph of different style w/ Long-form df by seaborn', fontsize=20)

plt.ylabel('Cummulative Num', fontsize=14)

plt.xlabel('Date', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

  3. pandas로 선 그래프 그리기 (Line Graph by pandas)

wide_df.head()

 # Line Graph by pandas

wide_df.plot.line()

plt.title('Line Graph with Wide-form df by pandas', fontsize=20)

plt.xlabel('Date', fontsize=14)

plt.ylabel('Cummulative Value', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

# accessed by calling the accessor as a method with the ``kind`` argument

wide_df.plot(kind='line')

plt.show()

long_df.head(n=8)

# Line plot w/ Long-form df by pandas

fig, ax = plt.subplots()

for key, grp in long_df.groupby('Group'):

    ax = grp.plot(ax=ax, kind='line', x='Date', y='CumVal', label=key)

plt.title('Line Graph with Long-form df by pandas', fontsize=20)

plt.xlabel('Date', fontsize=14)

plt.ylabel('Cummulative Value', fontsize=14)

plt.legend(fontsize=12, loc='best')

plt.show()

(1) 산점도 (Scatter Plot)

(2) 그룹별 산점도 (Scatter Plot by Groups)

(3) 4개 변수로 산점도 크기 및 색깔 다르게 그리기 (Scatterplot with 4 variables)

(4) 산점도 행렬 (Scatter Plot Matrix)

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

# iris data loading

iris = sns.load_dataset('iris')

iris.shape

(150, 5)

iris.head()

  (1) seaborn을 이용한 산점도 행렬 (scatterplot matrix by seaborn)

# scatterplot matrix with histogram only for continuous variables

sns.pairplot(iris, diag_kind='hist')

plt.show()

# Scatterplot matrix with different color by group and kde

sns.pairplot(iris, 

             diag_kind='kde',

             hue="species", 

             palette='bright') # pastel, bright, deep, muted, colorblind, dark

plt.show()

  (2) pandas를 이용한 산점도 행렬 (scatterplot matrix by pandas)

# scatterplot matrix by pandas scatter_matrix()

from pandas.plotting import scatter_matrix

scatter_matrix(iris, 

               alpha=0.5, 

               figsize=(8, 8), 

               diagonal='kde')

plt.show()

  (3) plotly를 이용한 산점도 행렬 (interactive scatterplot matrix by plotly)

# import plotly standard

import plotly.plotly as py

import plotly.graph_objs as go

import plotly.figure_factory as ff

# Cufflinks wrapper on plotly

import cufflinks as cf

# Display all cell outputs

from IPython.core.interactiveshell import InteractiveShell

# plotly + cufflinks in offline mode

from plotly.offline import iplot

cf.go_offline()

# set the global theme

cf.set_config_file(world_readable=True, theme='pearl', offline=True)

fig = ff.create_scatterplotmatrix(

    iris[['petal_width', 'petal_length', 'sepal_width', 'sepal_length']],

    height=800,

    width=800, 

    diag='histogram') # scatter, histogram, box

iplot(fig) # offline mode

# scatterplot matrix by plotly with box plot at diagonal & different color by index(GROUP)

fig = ff.create_scatterplotmatrix(

    iris,

    height=800,

    width=800, 

    diag='box', # scatter, histogram, box

    index='species')

iplot(fig)

(1) 산점도 (Scatter Plot)

(2) 그룹별 산점도 (Scatter Plot by Groups)

(3) 4개 변수로 점의 크기와 색을 다르게 산점도 그리기 (Scatter plot with different size, color)

(4) 산점도 행렬 (Scatter Plot Matrix)

# importing libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

plt.rcParams['figure.figsize'] = [10, 8] # setting figure size

# loading 'iris' dataset from seaborn

iris = sns.load_dataset('iris')

iris.shape

(150, 5)

iris.head()

  (1) matplotlib에 의한 4개 연속형 변수를 사용한 산점도 (X축, Y축, 색, 크기)

# set the size

plt.rcParams['figure.figsize'] = [10, 8]

# remove ticks and values of axis

plt.xticks([])

plt.yticks([])

# markers' shape

all_shape=['.','o','v','^','>','<','s','p','*','h','H','D', 'd', '', '', '']

num = 0

for x in range(1, 5):

    for y in range(1, 5):

        num += 1

        plt.plot(x, y, 

                 marker = all_shape[num-1], 

                 markerfacecolor='green', 

                 markersize=20, 

                 markeredgecolor='black')

        plt.text(x+0.1, y, 

                 all_shape[num-1], 

                 horizontalalignment='left', 

                 size='medium', 

                 color='black', 

                 weight='semibold')

plt.title('Markers', fontsize=20)        

plt.show()