linr, logr

1 files changed, 38 insertions, 4 deletions

diff --git a/R_LinR/main.r b/R_LinR/main.r
index d7b5856..3bb98fb 100755
--- a/R_LinR/main.r
+++ b/R_LinR/main.r
@@ -5,7 +5,7 @@ df <- subset(df, sex == "F")
 df <- subset(df, select = -c(zcta, sex))
 df <- subset(df, 8 < meaneducation & meaneducation < 18)
 df <- subset(df, 10000 < meanhouseholdincome & meanhouseholdincome < 200000)
-df <- subset(df, 10000 < meanhouseholdincome & meanhouseholdincome < 200000)
+df <- subset(df, 0 < meanemployment & meanemployment < 3)
 df <- subset(df, 20 < meanage & meanage < 60)
 
 df$log_income <- log10(df$meanhouseholdincome)
@@ -15,12 +15,46 @@ names(df) <- c("X", "age", "education", "employment", "income", "log_income")
 
 library(ggplot2)
 
-ggplot(df, aes(x = age, y = log_income)) +
-  geom_point(alpha = 0.2) +
-  labs(x = "age", y = "income", title = "log_income(age)")
+# b
 
 model <- lm(log_income ~ age, df)
 
+# a
 
+ggplot(df, aes(x = age, y = log_income)) +
+  geom_point(alpha = 0.2) +
+  geom_abline(
+    intercept = coef(model)[1],
+    slope = coef(model)[2],
+    color = "red",
+    size = 1
+  ) +
+  labs(x = "age", y = "income", title = "log_income(age)")
+
+# bcde
 print(model)
 summary(model)
+
+model_2 <- lm(log_income ~ education, df)
+print(model_2)
+summary(model_2)
+
+ggplot(df, aes(x = education, y = log_income)) +
+  geom_point(alpha = 0.2) +
+  geom_abline(
+    intercept = coef(model_2)[1],
+    slope = coef(model_2)[2],
+    color = "red",
+    size = 1
+  ) +
+  labs(x = "education", y = "income", title = "log_income(education)")
+
+
+model_3 <- lm(log_income ~ education + age + employment, df)
+print(model_3)
+summary(model_3)
+
+ggplot(df) +
+  geom_point(aes(x = log_income, y = fitted(model_3)), alpha = 0.2) +
+  geom_line(aes(x = log_income, y = log_income), col = "red") +
+  labs(x = "actual", y = "predicted")