This a snapshot of part of the data that i am using to run a linear regression m

Question

This a snapshot of part of the data that i am using to run a linear regression model in Azure ML, should i remove any of the columns from the data set before uploading to Azure?

CARAT WEIGHT CUT CLARITY DEPTH % POLISH GIRDLE FLUORESCENCE SHAPE COLOR LENGTH/WIDTH RATIO TABLE % SYMMETRY CULET LENGTH WIDTH HEIGHT PRICE 0.8 Ideal VS1 62% Excellent Thin to Slightly Thick None Round D 1.01 58% Very Good None 5.89 5.93 3.68 4504 1.01 Very Good VS1 68% Very Good Thin to Slightly Thick None Radiant F 1.24 67% Very Good None 6.5 5.26 4 5448 0.41 Very Good SI1 62% Excellent Slightly Thick to Thick, Faceted None Round F 1 58% Excellent None 4.75 4.77 3 966 0.5 Very Good SI1 61% Excellent Medium to Slightly Thick None Round G 1 56% Good None 5.11 5.12 3.14 1257 0.36 Very Good VVS1 64% Very Good Slightly Thick None Round J 1 56% Very Good None 4.53 4.51 3 554 0.33 Sig. Ideal VVS2 62% Excellent Thin None Round E 1.01 55% Excellent None 4.46 4.43 3 889 0.9 Very Good VS2 66% Excellent Thick None Asscher H 1.02 61% Very Good None 5.37 5.25 3.44 2629.8 0.67 Very Good SI1 69% Excellent Very Thick None Emerald H 1.4 59% Excellent None 5.84 4.16 3 1211 0.51 Very Good SI1 67% Excellent Very Thin to Thick None Cushion I 1.06 62% Very Good None 4.7 4.42 3 732 0.49 Very Good SI1 62% Very Good Thin to Slightly Thick None Oval H 1.38 61% Very Good None 6.17 4.48 3 628 0.77 Good VS2 62% Good Very Thin to Medium Faint Round E 1.01 60% Good None 5.85 5.9 4 3712 2 Very Good SI1 63% Very Good Very Thick to Extremely Thick Faint Pear E 1.45 55% Good None 10.28 7.08 4 19086 0.3 Good VVS2 67% Excellent Slightly Thick to Very Thick None Round G 1.01 59% Very Good None 4.05 4.08 3 580 0.51 Ideal VS2 62% Excellent Thin to Medium Medium Round D 1.01 57% Very Good None 5.16 5.13 3 1820 0.3 Ideal VS2 61% Excellent Medium to Slightly Thick Faint Round G 1 58% Excellent None 4.32 4.34 2.63 551.1 0.71 Ideal VVS1 62% Very Good Medium to Slightly Thick, Faceted None Round E 1.01 58% Excellent None 5.72 5.68 3.55 4365.79

Explanation / Answer

From the given partial data, it is observed that response variable is price.

Model trying to fit is linear regression. So one can check for the correlation of response variable with the independent variables. On doing this it is observed that depth feature has low correlation with price (Caution : But this is observed with the given partial data). Hence column depth can be removed.

Related Questions

Navigate

• Browse (All)
• Browse T
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.