MBA 563 Template For Assignment 3
Sadaf Rizvi
2024-11-18 00:00:32.542812
Load any libraries here
#install.packages("tidyverse")
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors#install.packages("latexpdf")
library(latexpdf)1 - Load data
df <- read.csv("store_3.csv")2 - Familiarization with the data
summary(df)## store city region province
## Min. : 105 Length:771 Length:771 Length:771
## 1st Qu.: 6226 Class :character Class :character Class :character
## Median :34438 Mode :character Mode :character Mode :character
## Mean :34226
## 3rd Qu.:59663
## Max. :98788
##
## size revenue units cost
## Min. : 276.0 Length:771 Min. : 42.65 Min. : 41.12
## 1st Qu.: 671.8 Class :character 1st Qu.: 911.85 1st Qu.: 1229.12
## Median : 792.5 Mode :character Median :1351.25 Median : 1843.41
## Mean : 755.5 Mean :1559.78 Mean : 2180.51
## 3rd Qu.: 893.0 3rd Qu.:1941.60 3rd Qu.: 2689.76
## Max. :1163.0 Max. :9715.83 Max. :14228.89
## NA's :15
## gross_profit promo_units energy_units regularBars_units
## Min. : 36.36 Min. : 17.5 Min. : 4.1 Min. : 5.10
## 1st Qu.: 771.74 1st Qu.: 344.4 1st Qu.: 142.7 1st Qu.: 75.67
## Median : 1150.93 Median : 499.3 Median : 215.6 Median :110.65
## Mean : 1388.03 Mean : 567.0 Mean : 253.0 Mean :123.95
## 3rd Qu.: 1702.92 3rd Qu.: 730.5 3rd Qu.: 317.1 3rd Qu.:154.84
## Max. :10457.82 Max. :3116.5 Max. :1576.3 Max. :681.56
##
## gum_units bagpegCandy_units isotonics_units singleServePotato_units
## Min. : 1.88 Min. : 0.00 Min. : 3.98 Min. : 1.75
## 1st Qu.: 53.49 1st Qu.: 24.43 1st Qu.: 57.79 1st Qu.: 29.51
## Median : 77.88 Median : 41.65 Median : 84.48 Median : 44.92
## Mean : 85.53 Mean : 50.33 Mean : 98.76 Mean : 56.34
## 3rd Qu.:110.11 3rd Qu.: 63.72 3rd Qu.:124.16 3rd Qu.: 67.84
## Max. :318.69 Max. :381.96 Max. :562.46 Max. :439.06
##
## takeHomePotato_units kingBars_units flatWater_units psd591Ml_units
## Min. : 0.00 Min. : 0.00 Min. : 11.96 Min. : 0.00
## 1st Qu.: 15.69 1st Qu.: 33.89 1st Qu.: 82.33 1st Qu.: 31.28
## Median : 28.85 Median : 49.87 Median : 128.98 Median : 48.25
## Mean : 38.05 Mean : 58.68 Mean : 158.03 Mean : 60.57
## 3rd Qu.: 49.31 3rd Qu.: 73.33 3rd Qu.: 190.32 3rd Qu.: 74.95
## Max. :360.19 Max. :471.19 Max. :1424.27 Max. :390.38
## str(df)## 'data.frame': 771 obs. of 20 variables:
## $ store : int 105 117 122 123 182 183 186 194 227 233 ...
## $ city : chr "BROCKVILLE" "BURLINGTON" "BURLINGTON" "BURLINGTON" ...
## $ region : chr "ONTARIO" "ONTARIO" "ONTARIO" "ONTARIO" ...
## $ province : chr "ON" "ON" "ON" "ON" ...
## $ size : int 496 875 691 763 784 NA 966 710 973 967 ...
## $ revenue : chr "984.7" "2629.32" "2786.73" "2834.49" ...
## $ units : num 470 1131 1229 1258 1950 ...
## $ cost : num 591 1622 1709 1720 2486 ...
## $ gross_profit : num 394 1008 1077 1115 1633 ...
## $ promo_units : num 210 401 450 477 665 ...
## $ energy_units : num 72.1 192.8 240.5 194.2 199.7 ...
## $ regularBars_units : num 38.6 75 93.7 99.4 175.5 ...
## $ gum_units : num 29.3 55.9 64.3 73.2 145.8 ...
## $ bagpegCandy_units : num 13.4 42.1 29.9 54.1 68.1 ...
## $ isotonics_units : num 20.7 87.6 105.7 118.2 109.3 ...
## $ singleServePotato_units: num 18.6 36.4 48 39.7 85.7 ...
## $ takeHomePotato_units : num 7.71 33.46 19.9 22.1 42.33 ...
## $ kingBars_units : num 17.9 47.4 45.2 45.3 79.8 ...
## $ flatWater_units : num 56.5 98.4 130.3 132.8 204.1 ...
## $ psd591Ml_units : num 39.7 38.7 47.3 39.9 50.3 ...head(df)## store city region province size revenue units cost gross_profit
## 1 105 BROCKVILLE ONTARIO ON 496 984.7 470.46 590.73 393.97
## 2 117 BURLINGTON ONTARIO ON 875 2629.32 1131.38 1621.58 1007.74
## 3 122 BURLINGTON ONTARIO ON 691 2786.73 1229.46 1709.45 1077.27
## 4 123 BURLINGTON ONTARIO ON 763 2834.49 1257.63 1719.61 1114.88
## 5 182 DON MILLS ONTARIO ON 784 4118.36 1949.50 2485.83 1632.53
## 6 183 DON MILLS ONTARIO ON NA 374.83 186.54 227.36 147.47
## promo_units energy_units regularBars_units gum_units bagpegCandy_units
## 1 210.23 72.13 38.63 29.29 13.38
## 2 401.46 192.77 75.04 55.85 42.15
## 3 450.04 240.48 93.73 64.27 29.85
## 4 476.83 194.21 99.44 73.25 54.15
## 5 664.71 199.73 175.48 145.81 68.06
## 6 79.23 34.23 17.06 11.71 3.73
## isotonics_units singleServePotato_units takeHomePotato_units kingBars_units
## 1 20.69 18.60 7.71 17.87
## 2 87.62 36.44 33.46 47.44
## 3 105.65 47.96 19.90 45.21
## 4 118.19 39.67 22.10 45.33
## 5 109.35 85.71 42.33 79.81
## 6 9.29 8.48 0.00 11.88
## flatWater_units psd591Ml_units
## 1 56.54 39.71
## 2 98.42 38.73
## 3 130.27 47.31
## 4 132.77 39.87
## 5 204.06 50.29
## 6 25.31 2.69tail(df)## store city region province size revenue units cost gross_profit
## 766 94285 UNKNOWN QUEBEC UNKNOWN 343 1121.61 534.63 678.85 442.75
## 767 95198 SOOKE WEST BC 707 2910.59 1305.92 1777.54 1133.05
## 768 95342 MAPLE RIDGE WEST BC 711 1786.36 789.38 1088.62 697.74
## 769 95849 VANCOUVER WEST BC 444 1497.23 703.52 902.25 594.97
## 770 97250 WINNIPEG WEST MB 723 2093.18 928.54 1325.07 768.11
## 771 98788 VANCOUVER WEST BC 885 3753.52 1644.13 2245.66 1507.87
## promo_units energy_units regularBars_units gum_units bagpegCandy_units
## 766 168.93 90.44 43.00 40.19 0.74
## 767 401.46 151.17 122.63 51.46 51.12
## 768 352.19 130.87 70.83 46.50 22.69
## 769 256.42 81.98 66.71 29.29 18.42
## 770 438.96 113.96 72.38 38.17 31.48
## 771 451.71 207.17 118.27 86.92 52.98
## isotonics_units singleServePotato_units takeHomePotato_units kingBars_units
## 766 34.22 22.07 3.15 32.93
## 767 85.21 46.25 30.15 74.52
## 768 52.69 19.02 14.58 22.52
## 769 72.29 24.83 7.60 26.60
## 770 68.37 30.00 27.44 38.67
## 771 105.87 68.38 38.83 47.79
## flatWater_units psd591Ml_units
## 766 49.00 18.00
## 767 110.79 43.27
## 768 73.54 32.15
## 769 86.15 24.88
## 770 93.10 59.35
## 771 195.31 37.75slice_sample(df, n=5)## store city region province size revenue units cost
## 1 655 RICHMOND HILL ONTARIO ON 758 2342.59 1020.90 1409.13
## 2 36531 EDMONTON WEST AB NA 733.04 341.25 438.89
## 3 14082 LONGUEUIL QUEBEC QC 875 2792.7 1215.62 1774.36
## 4 13303 MIRABEL QUEBEC QC 877 6314.35 2657.15 3795.51
## 5 398 LONDON ONTARIO ON 609 1372.67 625.35 857.48
## gross_profit promo_units energy_units regularBars_units gum_units
## 1 933.46 297.88 147.69 84.10 62.79
## 2 294.15 119.10 54.04 27.92 39.37
## 3 1018.35 536.52 303.35 91.85 66.17
## 4 2518.85 971.87 725.12 160.00 130.17
## 5 515.18 287.71 129.60 52.40 40.71
## bagpegCandy_units isotonics_units singleServePotato_units
## 1 36.12 71.02 29.37
## 2 3.96 22.31 11.65
## 3 28.94 65.50 28.13
## 4 62.37 195.67 89.00
## 5 12.58 56.69 19.92
## takeHomePotato_units kingBars_units flatWater_units psd591Ml_units
## 1 22.42 40.94 110.40 28.79
## 2 3.38 15.56 39.21 39.87
## 3 33.38 35.63 74.50 42.69
## 4 61.13 65.42 256.79 60.67
## 5 4.90 28.88 69.08 24.46n_distinct(df$city)## [1] 256n_distinct(df$region)## [1] 4unique(df$city)## [1] "BROCKVILLE" "BURLINGTON"
## [3] "DON MILLS" "NORTH YORK"
## [5] "ETOBICOKE" "GEORGETOWN"
## [7] "GORMLEY" "GUELPH"
## [9] "HAMILTON" "STONEY CREEK"
## [11] "KANATA" "KITCHENER"
## [13] "LONDON" "UNIONVILLE"
## [15] "SCARBOROUGH" "MILTON"
## [17] "MISSISSAUGA" "NEPEAN"
## [19] "NEWMARKET" "ORLEANS"
## [21] "OTTAWA" "GLOUCESTER"
## [23] "PICKERING" "PORT HOPE"
## [25] "RICHMOND HILL" "ST. CATHARINES"
## [27] "ST THOMAS" "SUDBURY"
## [29] "THORNHILL" "VAUGHAN"
## [31] "TORONTO" "CONCORD"
## [33] "WHITBY" "WIARTON"
## [35] "WINDSOR" "WOODBRIDGE"
## [37] "UNKNOWN" "AJAX"
## [39] "OAKVILLE" "TECUMSEH"
## [41] "BRAMPTON" "ARTHUR"
## [43] "AURORA" "BARRIE"
## [45] "BOLTON" "CALGARY"
## [47] "FORT ST. JOHN" "QUESNEL"
## [49] "EDMONTON" "ROCKY MOUNTAIN HOUSE"
## [51] "CHASE" "MAPLE RIDGE"
## [53] "PORT COQUITLAM" "WINFIELD"
## [55] "SURREY" "KAMLOOPS"
## [57] "VANCOUVER" "KELOWNA"
## [59] "REGINA" "ABBOTSFORD"
## [61] "MISSION" "WEST VANCOUVER"
## [63] "WINNIPEG" "VICTORIA"
## [65] "SASKATOON" "ST. ALBERT"
## [67] "NANOOSE BAY" "WILLIAMS LAKE"
## [69] "SALMON ARM" "LANGLEY"
## [71] "LAKE LOUISE" "BURNABY"
## [73] "RICHMOND" "PRINCE GEORGE"
## [75] "LADNER" "JASPER"
## [77] "GRAND FORKS" "LOGAN LAKE"
## [79] "WESTBANK" "NIAGARA-ON-THE-LAKE"
## [81] "BOWMANVILLE" "OSHAWA"
## [83] "COURTICE" "ST CATHARINES"
## [85] "WELLAND" "MARKHAM"
## [87] "ORILLIA" "WILLOWDALE"
## [89] "DOWNSVIEW" "EMERYVILLE"
## [91] "CAMBRIDGE" "WATERLOO"
## [93] "STRATFORD" "CHATHAM"
## [95] "SARNIA" "DORCHESTER"
## [97] "L'ASSOMPTION" "MONTRÉAL"
## [99] "BÉCANCOUR" "LAVAL"
## [101] "SAINTE-JULIE" "DELSON"
## [103] "SAINT-JEAN-PORT-JOLI" "STONEHAM-ET-TEWKESBURY"
## [105] "QUÉBEC" "HALIFAX"
## [107] "FALL RIVER" "BEDFORD"
## [109] "DARTMOUTH" "STEWIACKE"
## [111] "LOWER SACKVILLE" "CAP-ROUGE"
## [113] "SAINT-HUBERT" "DOLLARD DES ORMEAUX"
## [115] "GREENFIELD PARK" "ST-LAURENT"
## [117] "STE-HÉLÈNE-DE-BAGOT" "DORVAL"
## [119] "LACHINE" "BOUCHERVILLE"
## [121] "SAINT-LÉONARD" "LONGUEUIL"
## [123] "BROSSARD" "NEUFCHATEL"
## [125] "CHATEAUGUAY" "MONTRÉAL NORD"
## [127] "ANJOU" "SAINT-HYACINTHE"
## [129] "KIRKLAND" "DRUMMONDVILLE"
## [131] "SAINT-LAURENT" "GATINEAU"
## [133] "BOISBRIAND" "SAINT-MATHIEU-DE-BELOEIL"
## [135] "ANCIENNE-LORETTE" "CANDIAC"
## [137] "VAUDREUIL" "ANGE GARDIEN DE ROUVILLE"
## [139] "TROIS-RIVIÈRES" "MONCTON"
## [141] "MIRABEL" "VILLE MONT ROYAL"
## [143] "ST-JÉRÔME" "VERDUN"
## [145] "BEAUPORT" "REPENTIGNY"
## [147] "MONT-TREMBLANT" "SAINT JOHN"
## [149] "BROMONT" "VANIER"
## [151] "SHERBROOKE" "NORTH RIVER"
## [153] "BERTHIERVILLE" "TANTALLON"
## [155] "ST-NICOLAS" "LACHENAIE"
## [157] "MASCOUCHE" "ELMSDALE"
## [159] "LÉVIS" "BLAINVILLE"
## [161] "TERREBONNE" "LAPRAIRIE"
## [163] "BELOEIL" "LES CEDRES"
## [165] "CAP ST-IGNACE" "L'ISLET"
## [167] "LA POCATIÈRE" "SAINT-PHILIPPE"
## [169] "RIVIÈRE DU LOUP" "RIVIÈRE-DU-LOUP"
## [171] "TROIS-PISTOLES" "BRANTFORD"
## [173] "KINGSTON" "THUNDER BAY"
## [175] "PETERBOROUGH" "CUMBERLAND"
## [177] "STITTSVILLE" "BRADFORD"
## [179] "PARRY SOUND" "NIAGARA FALLS"
## [181] "MAIDSTONE" "LEDUC"
## [183] "SPRUCE GROVE" "MEDICINE HAT"
## [185] "WETASKIWIN" "DUGALD"
## [187] "STONY PLAIN" "CHILLIWACK"
## [189] "GRANDE PRAIRIE" "MORRIS"
## [191] "LANGENBURG" "AIRDRIE"
## [193] "FORT MCMURRAY" "SHERWOOD PARK"
## [195] "ACHESON" "CHESTERMERE"
## [197] "ALDERSYDE" "ROCKY VIEW"
## [199] "CALEDON" "CAMPBELLVILLE"
## [201] "WATERDOWN" "DUNDAS"
## [203] "SUTTON WEST" "NIPIGON"
## [205] "BELLEVILLE" "NAPANEE"
## [207] "SMITHVILLE" "SCHOMBERG"
## [209] "LAC DU BONNET" "BRANDON"
## [211] "PORTAGE LA PRAIRIE" "SELKIRK"
## [213] "OAK BLUFF" "CORNWALL"
## [215] "KESWICK" "TRENTON"
## [217] "WOODSTOCK" "COBOURG"
## [219] "ST. THOMAS" "THORNTON"
## [221] "HAVELOCK" "ACTON"
## [223] "INGERSOLL" "OWEN SOUND"
## [225] "HORNBY" "BEAVERTON"
## [227] "MERRITT" "PEMBERTON"
## [229] "GIBSONS" "COQUITLAM"
## [231] "PEACHLAND" "VERNON"
## [233] "YORKTON" "MOOSE JAW"
## [235] "NORTH BATTLEFORD" "NISKU"
## [237] "BATTLEFORD" "CANMORE"
## [239] "RED DEER" "HINTON"
## [241] "LETHBRIDGE" "NORTH VANCOUVER"
## [243] "HOPE" "PORT ALBERNI"
## [245] "CAMPBELL RIVER" "COURTENAY"
## [247] "WHITE ROCK" "NEW WESTMINSTER"
## [249] "TSAWWASSEN" "NANAIMO"
## [251] "SORRENTO" "VALEMOUNT"
## [253] "PORT MOODY" "DELTA"
## [255] "PRINCETON" "SOOKE"Summary:
The data set has 771 observations across 20 variables. The variable size shows 15 NA’s to now be numeric. The variable revenue variable equals character type. 4 unique regions and 256 unique cities.
3 - Convert revenue to numeric
df$revenue <- as.numeric(df$revenue)## Warning: NAs introduced by coercionstr(df)## 'data.frame': 771 obs. of 20 variables:
## $ store : int 105 117 122 123 182 183 186 194 227 233 ...
## $ city : chr "BROCKVILLE" "BURLINGTON" "BURLINGTON" "BURLINGTON" ...
## $ region : chr "ONTARIO" "ONTARIO" "ONTARIO" "ONTARIO" ...
## $ province : chr "ON" "ON" "ON" "ON" ...
## $ size : int 496 875 691 763 784 NA 966 710 973 967 ...
## $ revenue : num 985 2629 2787 2834 4118 ...
## $ units : num 470 1131 1229 1258 1950 ...
## $ cost : num 591 1622 1709 1720 2486 ...
## $ gross_profit : num 394 1008 1077 1115 1633 ...
## $ promo_units : num 210 401 450 477 665 ...
## $ energy_units : num 72.1 192.8 240.5 194.2 199.7 ...
## $ regularBars_units : num 38.6 75 93.7 99.4 175.5 ...
## $ gum_units : num 29.3 55.9 64.3 73.2 145.8 ...
## $ bagpegCandy_units : num 13.4 42.1 29.9 54.1 68.1 ...
## $ isotonics_units : num 20.7 87.6 105.7 118.2 109.3 ...
## $ singleServePotato_units: num 18.6 36.4 48 39.7 85.7 ...
## $ takeHomePotato_units : num 7.71 33.46 19.9 22.1 42.33 ...
## $ kingBars_units : num 17.9 47.4 45.2 45.3 79.8 ...
## $ flatWater_units : num 56.5 98.4 130.3 132.8 204.1 ...
## $ psd591Ml_units : num 39.7 38.7 47.3 39.9 50.3 ...4 - Delete rows with missing values
df <- na.omit(df)5 - df_low and df_high
mean(df$revenue)## [1] 3628.561df_low <- df %>% filter(revenue < 3628)
mean(df_low$size)## [1] 679.6025mean(df$revenue)## [1] 3628.561df_high <- df %>% filter(revenue >= 3628)
mean(df_high$size)## [1] 882.4929Comment about the relationship between revenue and size by discussing means.
Average size of df_low is 679.6 and Average size of df_high is 882.
6 - Correlation betweeen revenue and size
cor(df$revenue, df$size)## [1] 0.6175055ggplot(df, aes(x=size, y=revenue)) + geom_point()
Comment on the output from above.
When the size increases, revenue increases as well.
7 - Boxplots of revenue for each region
ggplot(df, aes(x=region, y=revenue)) +
geom_boxplot() +
labs(title = 'Boxplots of Revenue by Region')
Comment summary distribution of revenue within each region.
Atlantic area shows no outliers within range of revenue values. Ontario area shows most concentrated for revenue value. Quebec region shows small range of revenue values very few outliers. West region reflects a big range of revenue values, with the largest amount of outliers with highest revenue outliers.
8 - Bar chart of gross_profit for each province
province <- df %>% group_by(province) %>% summarize(sum_revenue = sum(revenue))
print(province)## # A tibble: 10 × 2
## province sum_revenue
## <chr> <dbl>
## 1 AB 542720.
## 2 BC 419288.
## 3 MB 84681.
## 4 NB 13869.
## 5 NS 44021.
## 6 ON 1046387.
## 7 PE 4511.
## 8 QC 470365.
## 9 SK 83426.
## 10 UNKNOWN 30296.ggplot(data = df, aes(x = province, y = revenue)) +
geom_col() +
scale_y_continuous(labels = scales::unit_format(unit = "M", scale = 1e-6)) +
labs(title = 'Total Gross Profit by Province')
Summary Comment:
Ontario has the highest total gross profit which surpasses profits of other provinces. Alberta is second, Quebec shows to be third. British Columbia and Saskatchewan reflects less total gross profits in comparison to the top producing provinces.
9 - Correlation matrix of average store sales for product categories
correlation_matrix <- cor(df[,11:20])
correlation_matrix## energy_units regularBars_units gum_units
## energy_units 1.0000000 0.7940865 0.7791820
## regularBars_units 0.7940865 1.0000000 0.7430876
## gum_units 0.7791820 0.7430876 1.0000000
## bagpegCandy_units 0.7578455 0.9127088 0.6865389
## isotonics_units 0.8837228 0.8913260 0.7204674
## singleServePotato_units 0.7856168 0.9105970 0.6758916
## takeHomePotato_units 0.7504980 0.8823330 0.6710437
## kingBars_units 0.7960175 0.9015765 0.6322488
## flatWater_units 0.7855815 0.8772875 0.7031540
## psd591Ml_units 0.8139704 0.8402457 0.5849746
## bagpegCandy_units isotonics_units
## energy_units 0.7578455 0.8837228
## regularBars_units 0.9127088 0.8913260
## gum_units 0.6865389 0.7204674
## bagpegCandy_units 1.0000000 0.9046627
## isotonics_units 0.9046627 1.0000000
## singleServePotato_units 0.8725405 0.8825922
## takeHomePotato_units 0.9237664 0.8697460
## kingBars_units 0.8739585 0.9024568
## flatWater_units 0.8637856 0.8905652
## psd591Ml_units 0.8275502 0.8766410
## singleServePotato_units takeHomePotato_units
## energy_units 0.7856168 0.7504980
## regularBars_units 0.9105970 0.8823330
## gum_units 0.6758916 0.6710437
## bagpegCandy_units 0.8725405 0.9237664
## isotonics_units 0.8825922 0.8697460
## singleServePotato_units 1.0000000 0.8676895
## takeHomePotato_units 0.8676895 1.0000000
## kingBars_units 0.8782217 0.8523930
## flatWater_units 0.9184280 0.8275743
## psd591Ml_units 0.8880491 0.8205825
## kingBars_units flatWater_units psd591Ml_units
## energy_units 0.7960175 0.7855815 0.8139704
## regularBars_units 0.9015765 0.8772875 0.8402457
## gum_units 0.6322488 0.7031540 0.5849746
## bagpegCandy_units 0.8739585 0.8637856 0.8275502
## isotonics_units 0.9024568 0.8905652 0.8766410
## singleServePotato_units 0.8782217 0.9184280 0.8880491
## takeHomePotato_units 0.8523930 0.8275743 0.8205825
## kingBars_units 1.0000000 0.8638809 0.8641337
## flatWater_units 0.8638809 1.0000000 0.8388392
## psd591Ml_units 0.8641337 0.8388392 1.0000000- Product categories that sell together the least.
- Product categories that sell together the most.
max_corr <- max(correlation_matrix)
min_corr <- min(correlation_matrix)indices_max_corr <- which(correlation_matrix == max_corr, arr.ind = TRUE)
indices_min_corr <- which(correlation_matrix == min_corr, arr.ind = TRUE)product_categories <- colnames(correlation_matrix)
category1_max_corr <- product_categories[indices_max_corr[1, 2]]
category2_max_corr <- product_categories[indices_max_corr[1, 1]]
category1_min_corr <- product_categories[indices_min_corr[1, 2]]
category2_min_corr <- product_categories[indices_min_corr[1, 1]]
correlation_matrix## energy_units regularBars_units gum_units
## energy_units 1.0000000 0.7940865 0.7791820
## regularBars_units 0.7940865 1.0000000 0.7430876
## gum_units 0.7791820 0.7430876 1.0000000
## bagpegCandy_units 0.7578455 0.9127088 0.6865389
## isotonics_units 0.8837228 0.8913260 0.7204674
## singleServePotato_units 0.7856168 0.9105970 0.6758916
## takeHomePotato_units 0.7504980 0.8823330 0.6710437
## kingBars_units 0.7960175 0.9015765 0.6322488
## flatWater_units 0.7855815 0.8772875 0.7031540
## psd591Ml_units 0.8139704 0.8402457 0.5849746
## bagpegCandy_units isotonics_units
## energy_units 0.7578455 0.8837228
## regularBars_units 0.9127088 0.8913260
## gum_units 0.6865389 0.7204674
## bagpegCandy_units 1.0000000 0.9046627
## isotonics_units 0.9046627 1.0000000
## singleServePotato_units 0.8725405 0.8825922
## takeHomePotato_units 0.9237664 0.8697460
## kingBars_units 0.8739585 0.9024568
## flatWater_units 0.8637856 0.8905652
## psd591Ml_units 0.8275502 0.8766410
## singleServePotato_units takeHomePotato_units
## energy_units 0.7856168 0.7504980
## regularBars_units 0.9105970 0.8823330
## gum_units 0.6758916 0.6710437
## bagpegCandy_units 0.8725405 0.9237664
## isotonics_units 0.8825922 0.8697460
## singleServePotato_units 1.0000000 0.8676895
## takeHomePotato_units 0.8676895 1.0000000
## kingBars_units 0.8782217 0.8523930
## flatWater_units 0.9184280 0.8275743
## psd591Ml_units 0.8880491 0.8205825
## kingBars_units flatWater_units psd591Ml_units
## energy_units 0.7960175 0.7855815 0.8139704
## regularBars_units 0.9015765 0.8772875 0.8402457
## gum_units 0.6322488 0.7031540 0.5849746
## bagpegCandy_units 0.8739585 0.8637856 0.8275502
## isotonics_units 0.9024568 0.8905652 0.8766410
## singleServePotato_units 0.8782217 0.9184280 0.8880491
## takeHomePotato_units 0.8523930 0.8275743 0.8205825
## kingBars_units 1.0000000 0.8638809 0.8641337
## flatWater_units 0.8638809 1.0000000 0.8388392
## psd591Ml_units 0.8641337 0.8388392 1.0000000