dataframe の取り扱い [2021 版]

1: df0 <- read.table(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
2: print(head(df0,5))

1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
2: df <- df0[,c(1,2,4)]
3: print(head(df,5))

1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
2: df <- df0[,c(1,2,4)]
3: dfo <- df[df$cat == "Out_of_Range",]  # 条件を満たす行を抽出
4: print(head(dfo,5))

1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
2: df <- df0[,c(1,2,4)]
3: dfo <- df[df$cat == "Out_of_Range",c(1,3)]
4: print(head(dfo,5))

1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
2: df <- df0[,c(1,2,4)]
3: dfo <- df[df$cat == "Out_of_Range",c(1,3)]
4: names(dfo)[2] <- "Out_of_Range"      # 列名の変更
5: print(head(dfo,5))

1: array <- list()   # c() でもよい.
2: array <- append(array, list(add_ele))  # list(add_ele) にしないと "データフレームの配列" にはならない点！！

 1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
 2: df <- df0[,c(1,2,4)]
 3: adf <- list()
 4: cats <- c("Out_of_Range","Fat_Burn","Cardio","Peak")
 5: for (cat in cats) {
 6:     dfo <- df[df$cat == cat,c(1,3)]
 7:     names(dfo)[2] <- cat
 8:     adf <- append(adf,list(dfo))
 9: }
10: print(head(adf[[2]],5))   # adf[[1]] 二重にかっこを付ける必要あり

1: mdf <- adf[  1 ]  # shift(@adf) で最初の要素を取り出す部分
2: adf <- adf[ -1 ]  # shift(@adf) 最初の要素を削除する部分

 1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
 2: df <- df0[,c(1,2,4)]
 3: adf <- list()
 4: cats <- c("Out_of_Range","Fat_Burn","Cardio","Peak")
 5: for (cat in cats) {
 6:     dfo <- df[df$cat == cat,c(1,3)]
 7:     names(dfo)[2] <- cat
 8:     adf <- append(adf,list(dfo))
 9: }
10: # shift(@adf)
11: mdf <- adf[1]      # Out_of_Range
12: adf <- adf[-1]     # Fat_Burn, Cardio, Peak
13: for (ndf in adf) {
14:     mdf <- merge(mdf, ndf, by="date")    # 表の merge
15: }
16: print(head(mdf,5))

1: data <- c(1,2,5,7)
2: x <- Reduce(function(a,b) { a+b }, data)
3: x

 1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
 2: df <- df0[,c(1,2,4)]
 3: adf <- list()
 4: cats <- c("Out_of_Range","Fat_Burn","Cardio","Peak")
 5: for (cat in cats) {
 6:     dfo <- df[df$cat == cat,c(1,3)]
 7:     names(dfo)[2] <- cat
 8:     #print(head(dfo,5))
 9:     #adf[length(adf)+1] <- dfo
10:     adf <- append(adf,list(dfo))
11: }
12: mdf <- Reduce(function(d1,d2) merge(d1,d2,by="date"), adf)  # <-- ここ
13: print(head(mdf,5))

 1: df0 <- read.csv(file="data/heart_beats_summary_2021-02.data",header=TRUE, sep="\t")
 2: df <- df0[,c(1,2,4)]
 3: adf <- list()
 4: cats <- c("Out_of_Range","Fat_Burn","Cardio","Peak")
 5: for (cat in cats) {
 6:     dfo <- df[df$cat == cat,c(1,3)]
 7:     names(dfo)[2] <- cat
 8:     #print(head(dfo,5))
 9:     #adf[length(adf)+1] <- dfo
10:     adf <- append(adf,list(dfo))
11: }
12: mdf <- Reduce(function(d1,d2) merge(d1,d2,by="date"), adf)
13: write.csv(mdf,"data/r.csv", quote=FALSE, row.names=FALSE)

1: library(tidyverse)
2: df0 <- read_delim("data/heart_beats_summary_2021-02.data","\t")
3: print(head(df0,5))

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: df <- df0[,c(1,2,4)]   # <-- dataframe と同じでいける
4: print(head(df,5))

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: df <- df0[,c(1,2,4)]
4: dfo <- filter(df, cat=="Out_of_Range")  # <-- cat 列が "Out_of_Range" のもののみ抽出
5: print(head(dfo,5))

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: df <- df0[,c(1,2,4)]
4: dfo <- filter(df, cat=="Out_of_Range") %>% select(date,min) # <-- date, min 列だけ取り出す.
5: print(head(dfo,5))

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: df <- df0[,c(1,2,4)]
4: dfo0 <- filter(df, cat=="Out_of_Range")
5: dfo <- dfo0[,c(1,3)]  # <-- 1,3 列目だけ
6: print(head(dfo,5))

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: df <- df0[,c(1,2,4)]
4: dfo <- filter(df, cat=="Out_of_Range") %>% select(date,min) %>% rename(Out_of_Range = min)
5: print(head(dfo,5))

 1: library(tidyverse)
 2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
 3: df <- df0[,c(1,2,4)]
 4: cats <- c("Out_of_Range", "Fat_Burn", "Cardio", "Peak")
 5: adf <- list()
 6: for (x in cats) {
 7:     #dfo <- filter(df, cat==x) %>% select(date,min) %>% rename(x = min) # これだと x という文字列が入ってしまう.
 8:     dfo <- filter(df, cat==x) %>% select(date,min) %>% rename(!!x := min)
 9:     adf <- append(adf,list(dfo))
10: }
11: print(head(adf[[2]],5))

 1: library(tidyverse)
 2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
 3: df <- df0[,c(1,2,4)]
 4: cats <- c("Out_of_Range", "Fat_Burn", "Cardio", "Peak")
 5: adf <- list()
 6: for (x in cats) {
 7:     dfo <- filter(df, cat==x) %>% select(date,min) %>% rename(!!x := min)
 8:     adf <- append(adf,list(dfo))
 9: }
10: mdf <- adf[[1]]
11: adf <- adf[-1]
12: for (ndf in adf) {
13:     mdf <- full_join(mdf, ndf, by="date")
14: }
15: print(head(mdf,5))

 1: library(tidyverse)
 2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
 3: df <- df0[,c(1,2,4)]
 4: cats <- c("Out_of_Range", "Fat_Burn", "Cardio", "Peak")
 5: adf <- list()
 6: for (x in cats) {
 7:     dfo <- filter(df, cat==x) %>% select(date,min) %>% rename(!!x := min)
 8:     adf <- append(adf,list(dfo))
 9: }
10: mdf <- adf %>% reduce(full_join, by="date")   # <-- ここ
11: print(head(mdf,5))

 1: library(tidyverse)
 2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
 3: df <- df0[,c(1,2,4)]
 4: cats <- c("Out_of_Range", "Fat_Burn", "Cardio", "Peak")
 5: adf <- list()
 6: for (x in cats) {
 7:     dfo <- filter(df, cat==x) %>% select(date,min) %>% rename(!!x := min)
 8:     adf <- append(adf,list(dfo))
 9: }
10: mdf <- adf %>% reduce(full_join, by="date")
11: write_csv(mdf,"data/rv.csv")

1: import pandas as pd
2: df = pd.read_csv('data/heart_beats_summary_2021-02.data',sep='\t', header=0, parse_dates=[0])
3: df2 = df.iloc[:,[0,1,3]]
4: print(df2.head(5))

1: import pandas as pd
2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0])
3: print(df.iat[0,1])    # 0 行 1 列目(0-based)の値
4: #print(df.iloc[::,2])
5: print(df.iloc[: ,2].head(5))  # 全行 2列目(0-based)

1: import pandas as pd
2: df = pd.read_csv("data/heart_beats_summary_2021-02.data",sep="\t",header=0, parse_dates=[0], usecols=[0,1,3])
3: print(df.head(5))

1: import pandas as pd
2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
3: dfo = df[df['cat']=='Out_of_Range']
4: # dfo = df[df.iloc[:,1]=='Out_of_Range']
5: # dfo = df[df.loc[:,'cat']=='Out_of_Range']
6: print(dfo.head(5))

1: import pandas as pd
2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
3: dfo = df[df['cat']=='Out_of_Range'].iloc[:,[0,2]]
4: #dfo = df[df.iloc[:,1]=='Out_of_Range'].iloc[:,[0,2]]
5: #dfo = df[df.loc[:,'cat']=='Out_of_Range'].loc[:,['date','min']]  # loc でも出来る.
6: print(dfo.head(5))

1: import pandas as pd
2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
3: dfo = df[df['cat']=='Out_of_Range'].iloc[:,[0,2]]
4: dfo.columns = ['date','Out_of_Range']  # column 名を指定し直し
5: print(dfo.head(5))

 1: import pandas as pd
 2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
 3: dfo = df[df['cat']=='Out_of_Range'].iloc[:,[0,2]]
 4: dff = df[df['cat']=='Fat_Burn'].iloc[:,[0,2]]
 5: dfc = df[df['cat']=='Cardio'].iloc[:,[0,2]]
 6: dfp = df[df['cat']=='Peak'].iloc[:,[0,2]]
 7: dfo.columns = ['date','Out_of_Range']
 8: dff.columns = ['date','Fat_Burn']
 9: dfc.columns = ['date','Cardio']
10: dfp.columns = ['date','Peak']
11: print(dfo.head(3))
12: print(dff.head(3))
13: print(dfc.head(3))
14: print(dfp.head(3))

1: import pandas as pd
2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
3: adf =[]
4: for cat in ('Out_of_Range','Fat_Burn','Cardio','Peak'):
5:     dfx = df[df['cat'] == cat].iloc[:,[0,2]]
6:     dfx.columns = ['date',cat]
7:     print(dfx.head(3))
8:     adf.append(dfx)

1: df3 = df1.merge(df2, on='date')  <-- df1 と df2 を date 列で merge して df3 に格納

 1: import pandas as pd
 2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
 3: adf =[]
 4: for cat in ('Out_of_Range','Fat_Burn','Cardio','Peak'):
 5:     dfx = df[df['cat'] == cat].iloc[:,[0,2]]
 6:     dfx.columns = ['date',cat]
 7:     adf.append(dfx)
 8: mdf = adf.pop(0)   # 先頭の要素を取り出し.
 9: for d in adf:
10:     mdf = mdf.merge(d,on='date')
11: print(mdf.head(5))

 1: import pandas as pd
 2: df = pd.read_table("data/heart_beats_summary_2021-02.data",header=0, parse_dates=[0], usecols=[0,1,3])
 3: adf =[]
 4: for cat in ('Out_of_Range','Fat_Burn','Cardio','Peak'):
 5:     dfx = df[df['cat'] == cat].iloc[:,[0,2]]
 6:     dfx.columns = ['date',cat]
 7:     adf.append(dfx)
 8: mdf = adf.pop(0)   # 先頭の要素を取り出し.
 9: for d in adf:
10:     mdf = mdf.merge(d,on='date')
11: mdf.to_csv("data/h.csv",index=False)  # csv ファイルとして保存

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", DataFrame)
3: println(first(df,5))    # head の代わり
4: println(last(df,5))     # tail の代わり

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame)
3: print(first(df,5))    # head の代わり
4: print(last(df,5))     # tail の代わり

1: using CSV, DataFrames
2: df = DataFrame(CSV.File("data/heart_beats_summary_2021-02.data",delim="\t",select=[1,2,4]))
3: println(typeof(df))
4: println(first(df,5))

1: using CSV, DataFrames
2: df = CSV.File("data/heart_beats_summary_2021-02.data",delim="\t",select=[1,2,4]) |> DataFrame
3: println(typeof(df))
4: println(first(df,5))

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data", DataFrame; delim="\t",select=[1,2,4])
3: println(typeof(df))
4: println(first(df,5))

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame)
3: dfo = df[df.cat .== "Out_of_Range", :]
4: print(first(dfo,5))

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame);
3: dfo = df[df[:,2] .== "Out_of_Range", [1,3]];
4: print(first(dfo,5))

1: df[:, :A][1] = 3   # 代入
2: print(df)   # 変わらない
3: 
4: df[!,:A][1] = 3
5: print(df)   # 変わる

1: using CSV, DataFrames
2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame);
3: dfo = df[df[:,2] .== "Out_of_Range", [1,3]];
4: rename!(dfo, :min => :Out_of_Range)
5: print(first(dfo,5))

1: using CSV, DataFrames
2: cat = "Out_of_Range"
3: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame);
4: dfo = df[df[:,2] .== cat, [1,3]];
5: rename!(dfo, :min => cat)   # <-- ここ
6: print(first(dfo,5))

1: using CSV, DataFrames
2: cat = "Out_of_Range"
3: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4],DataFrame);
4: dfo = df[df[:,2] .== cat, [1,3]];
5: rename!(dfo, "min" => cat)
6: print(first(dfo,5))

 1: using CSV, DataFrames
 2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame);
 3: adf =[]
 4: for cat in ("Out_of_Range","Fat_Burn","Cardio","Peak")
 5:     dfo = df[df[:,2] .== cat, [1,3]]  # df の 2 列目の値が cat のだけ取り出す. [1,3] 列目だけ取り出す.
 6:     rename!(dfo,"min" => cat)  # dfo の min 列の名前を cat に変更. dfo を変更する.
 7:     push!(adf,dfo)
 8: end
 9: ddf = outerjoin(adf[1], adf[2],  adf[3], adf[4], on = :date);  # 4 つしか無いのでベタ書き
10: println(first(ddf,5))

 1: using CSV, DataFrames
 2: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", select=[1,2,4], DataFrame);
 3: adf =[]
 4: for cat in ("Out_of_Range","Fat_Burn","Cardio","Peak")
 5:     dfo = df[df[:,2] .== cat, [1,3]]  # df の 2 列目の値が cat のだけ取り出す. [1,3] 列目だけ取り出す.
 6:     rename!(dfo,"min" => cat)  # dfo の min 列の名前を cat に変更. dfo を変更する.
 7:     push!(adf,dfo)
 8: end
 9: ddf = outerjoin(adf[1], adf[2],  adf[3], adf[4], on = :date);
10: CSV.write("data/j.csv",ddf, delim=",")

 1: library(ggplot2)
 2: 
 3: # データをつくる
 4: X <- seq(-4,4, length=100)    # -4 から 4 まで. 100 分割したベクトルを作成
 5: Y <- dnorm(x=X, mean=0, sd=1) # y としてガウス関数
 6: df <- data.frame(xf=X,yf=Y)   # ggplot2 は dataframe を読み込む
 7: 
 8: p <- ggplot(data=df) + geom_line(mapping=aes(x=xf,y=yf))  # x,y は固定
 9: plot(p)
10: fname <- 'images/r0.png'
11: ggsave(p,file=fname,dpi=70)

1: # test.data には日付(date)と時刻(time 09:03:02) 列があるとする.
2: d <- read.table('test.data', sep='\t', header=TRUE)
3: # datetime という新しい列をつくるとき.
4: # datetime 列は "date time" とする
5: d$datetime <- paste(d$date, d$time, sep=' ')
6: # POSIX 形式に変換
7: d$datetime <- as.POSIXct(d$datetime)
8: p <- ggplot(data=d) + geom_lines(mapping=aes(x=datetime, y=Y))

1: library(tidyverse)
2: df <- read_csv("data/rv.csv")  # 作成したもの
3: p <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Out_of_Range))
4: plot(p)
5: fname = 'images/r01.png'
6: ggsave(p,file=fname,dpi=70)

1: library(ggplot2)
2: df <- read.csv(file='data/r.csv',header=TRUE)
3: df$date <- as.POSIXct(df$date)
4: p <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Out_of_Range))
5: plot(p)
6: fname = 'images/r03.png'
7: ggsave(p,file=fname,dpi=70)

1: library(tidyverse)
2: df <- read_csv("data/rv.csv")  # 作成したもの
3: p <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Out_of_Range), color="blue")
4: p <- p + geom_line(mapping=aes(x=date,y=Fat_Burn),color="orange") + ylab("min")
5: plot(p)
6: fname = 'images/r04.png'
7: ggsave(p,file=fname,dpi=70)

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: head(df0)

1: library(tidyverse)
2: df0 <- read_tsv("data/heart_beats_summary_2021-02.data")
3: p <- ggplot(data=df0) + geom_line(mapping=aes(x=date,y=min,color=cat))
4: plot(p)
5: fname = 'images/r05.png'
6: ggsave(p,file=fname, dpi=70)

 1: library(tidyverse)
 2: library(gridExtra)
 3: df <- read_csv("data/rv.csv")  # 作成したもの
 4: p1 <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Out_of_Range), color="blue") + xlab("")
 5: p2 <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Fat_Burn),     color="orange") + xlab("")
 6: p3 <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Cardio),       color="magenta") + xlab("")
 7: p4 <- ggplot(data=df) + geom_line(mapping=aes(x=date,y=Peak),         color="cyan")
 8: # grid.arrange(p1,p2,p3,p4,nrow=4)  # 4 つ縦に並べる
 9: h <- arrangeGrob(p1,p2,p3,p4,nrow=4)
10: fname = 'images/r06.png'
11: ggsave(h,file=fname,dpi=70)

 1: import matplotlib.pyplot as plt
 2: import numpy as np
 3: # データ作成例
 4: x = np.linspace(-4,4, 100)    # -4 から 4 まで 100 分割
 5: # ガウス関数 いちいち定義する必要あるのか... 面倒だなぁ.
 6: def gauss(x,mu,sig):
 7:    return np.exp(-np.power(x -mu, 2.0)/ (2*np.power(sig,2)))
 8: y = gauss(x,0,1)
 9: # データ作成例ここまで
10: # ここからグラフ作成
11: fig = plt.figure()            # plt クラスから figure object
12: ax = fig.add_subplot(1,1,1)   # figure から axes object (1 行 1 列の 1 番目のグラフ = 1 枚のグラフを全体に描く)
13: ax.plot(x,y)                  # axes object が一つのグラフを描画する
14: fig.show()
15: # グラフの保存
16: fname = 'images/p00.png'
17: fig.savefig(fname, format='png', dpi=70)

 1: import matplotlib.dates as mdates
 2: # 目盛の指定
 3: xloc = mdates.HourLocator(byhour=range(0,24,4))  # 0-24時間 まで, 4 時間おきに目盛
 4: # ax は作成された axes object
 5: ax.xaxis.set_major_locator(xloc)                 # minor_locator もある(補助目盛)
 6: # x 軸の文字列 format の指定
 7: xfmt = mdates.DateFormatter("%H:%M") # 目盛の書かせ方. ここでは 00:00 形式で
 8: ax.xaxis.set_major_formatter(xfmt)
 9: # x 軸の文字列を斜めに書くとき
10: labels = ax.get_xticklabels()
11: plt.setp(labels, rotation=45, fontsize=10)

 1: import calendar
 2: # ax は作成された axes object
 3: ax.set_title('heart beats summary')
 4: 
 5: ax.set_xlabel('Date')
 6: ax.set_ylabel('heart_beat')
 7: 
 8: dlst = calendar.monthrange(2021,4)[1]  # 月末日
 9: ax.set_xlim(dt.datetime(2021,4,1), dt.datetime(2021,4,dlst))
10: ylim = (50,200)
11: ax.set_ylim(*ylim)

1: # 積み上げ棒グラフなら
2: ax.bar(df.date, df.Out_of_Range)
3: ax.bar(df.date, df.Fat_Burn, bottom=df.Out_of_Range,color='green')
4: ax.bar(df.date, df.Cardio, bottom=df.Out_of_Range+df.Fat_Burn,color='orange')
5: ax.bar(df.date, df.Peak, bottom=df.Out_of_Range+df.Fat_Burn+df.Cardio,color='red')

1: # 描画
2: fig.show()
3: # 保存
4: fig.save("output.png", format="png", dpi=70)

 1: import pandas as pd
 2: import matplotlib.pyplot as plt
 3: import matplotlib.dates as mdates
 4: 
 5: df = pd.read_csv('data/h.csv',parse_dates=[0])
 6: 
 7: fig = plt.figure(dpi=100, figsize=(4,3))
 8: ax = fig.add_subplot(1,1,1)   # figure から axes object (1 行 1 列の 1 番目)
 9: ax.plot(df.date, df.Out_of_Range)
10: 
11: fname = 'images/p01.png'
12: fig.show()
13: fig.savefig(fname)

 1: import pandas as pd
 2: import matplotlib.pyplot as plt
 3: import matplotlib.dates as mdates
 4: 
 5: df = pd.read_csv('data/h.csv',parse_dates=[0])
 6: 
 7: fig = plt.figure(dpi=100, figsize=(5,3))
 8: ax = fig.add_subplot(1,1,1)   # figure から axes object (1 行 1 列の 1 番目)
 9: ax.plot(df.date, df.Out_of_Range)
10: 
11: # 横軸は時系列
12: xloc = mdates.DayLocator(bymonthday=None, interval=7)
13: xfmt = mdates.DateFormatter("%Y-%m-%d")
14: ax.xaxis.set_major_locator(xloc)
15: ax.xaxis.set_major_formatter(xfmt)
16: # 斜めに書く場合
17: labels = ax.get_xticklabels()
18: plt.setp(labels, rotation=45, fontsize=10)
19: 
20: fname = 'images/p02.png'
21: fig.show()
22: fig.savefig(fname)

 1: import pandas as pd
 2: import matplotlib.pyplot as plt
 3: import matplotlib.dates as mdates
 4: 
 5: df = pd.read_csv('data/h.csv',parse_dates=[0])
 6: 
 7: fig = plt.figure(dpi=100, figsize=(5,3))
 8: ax = fig.add_subplot(1,1,1)   # figure から axes object (1 行 1 列の 1 番目)
 9: ax.plot(df.date, df.Out_of_Range)
10: 
11: # 横軸は時系列
12: xloc = mdates.DayLocator(bymonthday=None, interval=7)
13: xfmt = mdates.DateFormatter("%Y-%m-%d")
14: ax.xaxis.set_major_locator(xloc)
15: ax.xaxis.set_major_formatter(xfmt)
16: # 斜めに書く場合
17: labels = ax.get_xticklabels()
18: plt.setp(labels, rotation=45, fontsize=10)
19: # 配置をいい感じにする
20: plt.tight_layout()
21: 
22: fname = 'images/p03.png'
23: fig.show()
24: fig.savefig(fname)

 1: import pandas as pd
 2: import matplotlib.pyplot as plt
 3: import matplotlib.dates as mdates
 4: 
 5: df = pd.read_csv('data/h.csv',parse_dates=[0])
 6: 
 7: fig = plt.figure(dpi=100, figsize=(5,3))
 8: ax = fig.add_subplot(1,1,1)   # figure から axes object (1 行 1 列の 1 番目)
 9: ax.plot(df.date, df.Out_of_Range, label='out_of_range')
10: # そのまま書いてけばいい
11: ax.plot(df.date, df.Fat_Burn, label='fat_burn')
12: # 凡例が必要か？
13: ax.legend(fontsize=10)
14: 
15: # 横軸は時系列
16: xloc = mdates.DayLocator(bymonthday=None, interval=7)
17: xfmt = mdates.DateFormatter("%Y-%m-%d")
18: ax.xaxis.set_major_locator(xloc)
19: ax.xaxis.set_major_formatter(xfmt)
20: # 斜めに書く場合
21: labels = ax.get_xticklabels()
22: plt.setp(labels, rotation=45, fontsize=10)
23: # 配置をいい感じにする
24: plt.tight_layout()
25: 
26: fname = 'images/p04.png'
27: fig.show()
28: fig.savefig(fname)

 1: import pandas as pd
 2: import matplotlib.pyplot as plt
 3: import matplotlib.dates as mdates
 4: 
 5: df = pd.read_csv('data/h.csv',parse_dates=[0])
 6: 
 7: fig = plt.figure(dpi=100, figsize=(3,5))
 8: ax1 = fig.add_subplot(2,1,1)   # figure から axes object (2 行 1 列の 1 番目)
 9: ax1.plot(df.date, df.Out_of_Range)
10: # 二つ目のグラフ
11: ax2 = fig.add_subplot(2,1,2, sharex=ax1) # 2 行 1 列の 2 番目, ax1 の x 軸を共有する
12: ax2.plot(df.date, df.Fat_Burn, color="green", marker='.') # データに . つきのグラフにしてみる
13: 
14: # 一つ目のグラフの x 軸ラベルは要らない
15: ax1.tick_params(labelbottom=False)
16: 
17: # 横軸は時系列
18: xloc = mdates.DayLocator(bymonthday=None, interval=7)
19: xfmt = mdates.DateFormatter("%Y-%m-%d")
20: ax2.xaxis.set_major_locator(xloc)
21: ax2.xaxis.set_major_formatter(xfmt)
22: # 斜めに書く場合
23: labels = ax2.get_xticklabels()
24: plt.setp(labels, rotation=45, fontsize=10)
25: 
26: # title
27: ax1.set_title('out_of_range',fontsize=10)
28: ax2.set_title('fat_burn', fontsize=10)
29: 
30: # 配置をいい感じにする
31: plt.tight_layout()
32: 
33: fname = 'images/p05.png'
34: fig.show()
35: fig.savefig(fname)

1: import pandas as pd
2: df = pd.read_csv("data/heart_beats_summary_2021-02.data",sep="\t",header=0, parse_dates=[0], usecols=[0,1,3])
3: print(df.head(5))

1: import pandas as pd
2: from plotnine import ggplot, geom_line, aes, ggsave
3: import plotnine
4: 
5: df = pd.read_csv("data/heart_beats_summary_2021-02.data",sep="\t",header=0, parse_dates=[0], usecols=[0,1,3])
6: p = ggplot() + geom_line(data=df, mapping=aes(x='date', y='min', color='cat'))
7: fname = 'images/p06.png'
8: ggsave(p,filename=fname, format='png',dpi=70)

1: import pandas as pd
2: from plotnine import ggplot, geom_line, aes, ggsave, theme, element_text
3: import plotnine
4: df = pd.read_csv("data/heart_beats_summary_2021-02.data",sep="\t",header=0, parse_dates=[0], usecols=[0,1,3])
5: p = ggplot() + geom_line(data=df, mapping=aes(x='date', y='min', color='cat'))
6: p = p + theme(axis_text_x = element_text(rotation=45, hjust=1))
7: fname = 'images/py07.png'
8: ggsave(p,filename=fname, format='png',dpi=70)

1: import pandas as pd
2: from plotnine import ggplot, geom_line, aes, ggsave, theme, element_text, facet_wrap
3: import plotnine
4: df = pd.read_csv("data/heart_beats_summary_2021-02.data",sep="\t",header=0, parse_dates=[0], usecols=[0,1,3])
5: p = ggplot(data=df, mapping=aes(x='date',y='min',color='cat')) + geom_line()
6: p = p + theme(axis_text_x = element_text(rotation=45, hjust=1)) + facet_wrap('~cat',nrow=4)
7: fname = 'images/py08.png'
8: ggsave(p,filename=fname, format='png',dpi=70)

 1: using PyPlot
 2: 
 3: # ダミーデータ
 4: x = range(0,2π, step=0.1)  # 0 から 2π まで 0.1刻みでベクトルデータを作成
 5: y = []
 6: z = []
 7: # sin と cos にする.
 8: for i in x
 9:     push!(y,sin(i))
10:     push!(z,cos(i))
11: end
12: 
13: # matplotlib と同様に書ける！！
14: fig = figure()
15: ax1 = fig.add_subplot(2,1,1)
16: ax1.plot(x,y)
17: 
18: ax2 = fig.add_subplot(2,1,2)
19: ax2.plot(x,z)
20: 
21: fig.tight_layout()
22: fname = "images/j00.png"
23: fig.savefig(fname)

 1: # 折れ線の場合
 2: plot(x,y, color="m", marker="o", markerfacecolor="r", linestyle="-", label=raw"$\sin(x)$")
 3: # 色: b=blue, g=green, r=red, c=cyan, m=magenta, y=yellow, k=black,w=white
 4: # マーカの種類: o=円, s=square, p=pentagon, *=star, +=プラス記号, D=ダイアモンド
 5: # markerfacecolor=マーカの色
 6: # linestyle=線の種類: -=実戦 --=破線, -.=破線(点入り) :=点線
 7: legend()  # label の文字を凡例として使う.
 8: 
 9: # 棒グラフ
10: bar(x,y)
11: 
12: # ヒストグラム
13: hist(data)
14: 
15: # 散布図
16: scatter(x,y)
17: 
18: title("hoo")
19: xlabel("x label")
20: ylabel("y label")
21: 
22: grid(true)
23: 
24: savefig("hoge.png")
25: 
26: #x 目盛り
27: x_ticks_name([1,2,3], ["first","second","third"]) # 1,2,3 のとこに first, second, third
28: 
29: # 範囲
30: xlim(0, π)
31: ylim(0, nothing)  # 上限が無いばあい. nothing を使う.

 1: using CSV, DataFrames, PyPlot
 2: df = CSV.read("data/j.csv",DataFrame)
 3: 
 4: fig = figure(dpi=100, figsize=(4,3))
 5: ax  = fig.add_subplot(1,1,1)
 6: ax.plot(df.date, df.Out_of_Range)
 7: 
 8: fig.tight_layout()
 9: fname="images/j01.png"
10: fig.savefig(fname)

 1: import matplotlib.pyplot as plt
 2: import matplotlib.dates as mdates
 3: ...
 4: xloc = mdates.DayLocator(bymonthday=None, interval=7)
 5: xfmt = mdates.DateFormatter("%Y-%m-%d")
 6: ax.xaxis.set_major_locator(xloc)
 7: ax.xaxis.set_major_formatter(xfmt)
 8: # 斜めに書く場合
 9: labels = ax.get_xticklabels()
10: plt.setp(labels, rotation=45, fontsize=10)

 1: using CSV, DataFrames, PyPlot
 2: df = CSV.read("data/j.csv",DataFrame)
 3: 
 4: fig = figure(dpi=100, figsize=(4,3))
 5: ax  = fig.add_subplot(1,1,1)
 6: ax.plot(df.date, df.Out_of_Range)
 7: 
 8: xloc = matplotlib.dates.DayLocator(interval=7)  # bymonthly=None <-- None なんて知らんというエラーになってしまったのでここは変更
 9: xfmt = matplotlib.dates.DateFormatter("%Y-%m-%d")
10: ax.xaxis.set_major_locator(xloc)
11: ax.xaxis.set_major_formatter(xfmt)
12: 
13: labels = ax.get_xticklabels()
14: plt.setp(labels, rotation=45, fontsize=10)
15: 
16: fig.tight_layout()
17: fname="images/j02.png"
18: fig.savefig(fname)

 1: using CSV, DataFrames, PyPlot
 2: df = CSV.read("data/j.csv",DataFrame)
 3: 
 4: fig = figure(dpi=100, figsize=(5,3))
 5: ax  = fig.add_subplot(1,1,1)
 6: ax.plot(df.date, df.Out_of_Range, label="out_of_range")
 7: ax.plot(df.date, df.Fat_Burn,     label="fat_burn")
 8: 
 9: ax.legend(fontsize=10)
10: 
11: xloc = matplotlib.dates.DayLocator(interval=7)  # bymonthly=None <-- None なんて知らんというエラー
12: xfmt = matplotlib.dates.DateFormatter("%Y-%m-%d")
13: ax.xaxis.set_major_locator(xloc)
14: ax.xaxis.set_major_formatter(xfmt)
15: 
16: labels = ax.get_xticklabels()
17: plt.setp(labels, rotation=45, fontsize=10)
18: 
19: fig.tight_layout()
20: fname="images/j04.png"
21: fig.savefig(fname)

 1: using CSV, DataFrames, PyPlot
 2: df = CSV.read("data/j.csv",DataFrame)
 3: 
 4: fig = figure(dpi=100, figsize=(3,5))
 5: ax1  = fig.add_subplot(2,1,1)
 6: ax1.plot(df.date, df.Out_of_Range, label="out_of_range")
 7: 
 8: ax2  = fig.add_subplot(2,1,2, sharex=ax1)
 9: ax2.plot(df.date, df.Fat_Burn,     label="fat_burn", color="green", marker=".")
10: 
11: # 上のグラフの x 軸ラベルは要らない
12: ax1.tick_params(labelbottom=false)
13: 
14: # ax2 の x 軸ラベル
15: xloc = matplotlib.dates.DayLocator(interval=7)  # bymonthly=None <-- None なんて知らんというエラー
16: xfmt = matplotlib.dates.DateFormatter("%Y-%m-%d")
17: ax2.xaxis.set_major_locator(xloc)
18: ax2.xaxis.set_major_formatter(xfmt)
19: labels = ax2.get_xticklabels()
20: plt.setp(labels, rotation=45, fontsize=10)
21: 
22: # title
23: ax1.set_title("out_of_range", fontsize=10)
24: ax2.set_title("fat_burn",     fontsize=10)
25: 
26: fig.tight_layout()
27: fname="images/j05.png"
28: fig.savefig(fname)

 1: using CSV, DataFrames
 2: 
 3: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", DataFrame);
 4: 
 5: using RCall
 6: R"""Sys.setenv(LANG="en")"""
 7: @rimport base as R
 8: @rlibrary ggplot2
 9: 
10: p = ggplot(data=df) + geom_line(mapping=aes(x=:date, y=:min, color=:cat))
11: fname = "images/j06.png"
12: ggsave(p,file=fname,dpi=70)

 1: using CSV, DataFrames
 2: 
 3: df = CSV.read("data/heart_beats_summary_2021-02.data",delim="\t", DataFrame);
 4: 
 5: using RCall
 6: R"""Sys.setenv(LANG="en")"""
 7: @rimport base as R              # org-babel でここがエラー？
 8: @rlibrary ggplot2               # org-babel でここがエラー？
 9: 
10: p = ggplot(data=df) + geom_line(mapping=aes(x=:date, y=:min, color=:cat))
11: p = p + facet_wrap("~cat",nrow=4)   # rotation=45 は使えないようだ.
12: fname = "images/j07.png"
13: ggsave(p,file=fname,dpi=70)