post_tr2_SG

Author: eyrei123

polars-groupby/README.md

@@ -4,10 +4,11 @@ You should create a new folder named aggregations on your computer and place eac
 
 Your download bundle contains the following files:
 
-course.parquet           - This file contains all data from both `maths.parquet` and `portuguese.parquet`.
-maths.parquet            - This file contains data relating to a mathematics class.
+course.parquet           - This file contains all data from both `math.parquet` and `portuguese.parquet`.
+math.parquet             - This file contains data relating to a mathematics class.
 portuguese.parquet       - This file contains data relating to a Portuguese language class.
-maths_classes.parquet    - This file contains data used in the time series analysis examples.
+student.txt              - This file defines every field in the above three files.
+math_classes.parquet     - This file contains data used in the time series analysis examples.
 
 tutorial_code.ipynb      - This file contains the code used in the tutorial.
 solutions.ipynb          - This file contains the solutions to the exercises.

polars-groupby/maths.parquet polars-groupby/math.parquetpolars-groupby/maths.parquet renamed to polars-groupby/math.parquet

@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 3,
    "id": "a6fc4149-3f32-477f-ae54-f529aea7c9d9",
    "metadata": {},
    "outputs": [
@@ -34,30 +34,30 @@
        "  white-space: pre-wrap;\n",
        "}\n",
        "</style>\n",
-       "<small>shape: (1, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>middle_result</th><th>most_frequent_result</th><th>variance</th></tr><tr><td>f64</td><td>i64</td><td>f64</td></tr></thead><tbody><tr><td>11.0</td><td>10</td><td>20.989616</td></tr></tbody></table></div>"
+       "<small>shape: (1, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>median_result</th><th>most_frequent_result</th><th>variance</th></tr><tr><td>f64</td><td>i64</td><td>f64</td></tr></thead><tbody><tr><td>11.0</td><td>10</td><td>20.989616</td></tr></tbody></table></div>"
       ],
       "text/plain": [
        "shape: (1, 3)\n",
        "┌───────────────┬──────────────────────┬───────────┐\n",
-       "│ middle_result ┆ most_frequent_result ┆ variance  │\n",
+       "│ median_result ┆ most_frequent_result ┆ variance  │\n",
        "│ ---           ┆ ---                  ┆ ---       │\n",
        "│ f64           ┆ i64                  ┆ f64       │\n",
        "╞═══════════════╪══════════════════════╪═══════════╡\n",
        "│ 11.0          ┆ 10                   ┆ 20.989616 │\n",
        "└───────────────┴──────────────────────┴───────────┘"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "math_students = pl.read_parquet(\"maths.parquet\")\n",
+    "math_students = pl.read_parquet(\"math.parquet\")\n",
     "\n",
     "(\n",
     "    math_students.select(\n",
-    "        middle_result=pl.col(\"G3\").median(),\n",
+    "        median_result=pl.col(\"G3\").median(),\n",
     "        most_frequent_result=pl.col(\"G3\").mode(),\n",
     "        variance=pl.col(\"G3\").var(),\n",
     "    )\n",
@@ -183,10 +183,10 @@
     }
    ],
    "source": [
-    "maths_attendance = pl.read_parquet(\"maths_classes.parquet\")\n",
+    "math_attendance = pl.read_parquet(\"math_classes.parquet\")\n",
     "\n",
     "(\n",
-    "    maths_attendance.group_by_dynamic(\n",
+    "    math_attendance.group_by_dynamic(\n",
     "        index_column=\"class_start\",\n",
     "        every=\"1mo\",\n",
     "        closed=\"both\",\n",

polars-groupby/maths_classes.parquet polars-groupby/math_classes.parquetpolars-groupby/maths_classes.parquet renamed to polars-groupby/math_classes.parquet

@@ -0,0 +1,41 @@
+# Attributes for both student-mat.csv (Math course) and student-por.csv (Portuguese language course) datasets:
+0 subject - subject (binary: "M" - Math or "P" - Portuguese language)
+1 school - student's school (binary: "GP" - Gabriel Pereira or "MS" - Mousinho da Silveira)
+2 sex - student's sex (binary: "F" - female or "M" - male)
+3 age - student's age (numeric: from 15 to 22)
+4 address - student's home address type (binary: "U" - urban or "R" - rural)
+5 famsize - family size (binary: "LE3" - less or equal to 3 or "GT3" - greater than 3)
+6 Pstatus - parent's cohabitation status (binary: "T" - living together or "A" - apart)
+7 Medu - mother's education (numeric: 0 - none,  1 - primary education (4th grade), 2 – 5th to 9th grade, 3 – secondary education or 4 – higher education)
+8 Fedu - father's education (numeric: 0 - none,  1 - primary education (4th grade), 2 – 5th to 9th grade, 3 – secondary education or 4 – higher education)
+9 Mjob - mother's job (nominal: "teacher", "health" care related, civil "services" (e.g. administrative or police), "at_home" or "other")
+10 Fjob - father's job (nominal: "teacher", "health" care related, civil "services" (e.g. administrative or police), "at_home" or "other")
+11 reason - reason to choose this school (nominal: close to "home", school "reputation", "course" preference or "other")
+12 guardian - student's guardian (nominal: "mother", "father" or "other")
+13 traveltime - home to school travel time (numeric: 1 - <15 min., 2 - 15 to 30 min., 3 - 30 min. to 1 hour, or 4 - >1 hour)
+14 studytime - weekly study time (numeric: 1 - <2 hours, 2 - 2 to 5 hours, 3 - 5 to 10 hours, or 4 - >10 hours)
+15 failures - number of past class failures (numeric: n if 1<=n<3, else 4)
+16 schoolsup - extra educational support (binary: yes or no)
+17 famsup - family educational support (binary: yes or no)
+18 paid - extra paid classes within the course subject (Math or Portuguese) (binary: yes or no)
+19 activities - extra-curricular activities (binary: yes or no)
+20 nursery - attended nursery school (binary: yes or no)
+21 higher - wants to take higher education (binary: yes or no)
+22 internet - Internet access at home (binary: yes or no)
+23 romantic - with a romantic relationship (binary: yes or no)
+24 famrel - quality of family relationships (numeric: from 1 - very bad to 5 - excellent)
+25 freetime - free time after school (numeric: from 1 - very low to 5 - very high)
+26 goout - going out with friends (numeric: from 1 - very low to 5 - very high)
+27 Dalc - workday alcohol consumption (numeric: from 1 - very low to 5 - very high)
+28 Walc - weekend alcohol consumption (numeric: from 1 - very low to 5 - very high)
+29 health - current health status (numeric: from 1 - very bad to 5 - very good)
+30 absences - number of school absences (numeric: from 0 to 93)
+
+# these grades are related with the course subject, Math or Portuguese:
+31 G1 - first period grade (numeric: from 0 to 20)
+31 G2 - second period grade (numeric: from 0 to 20)
+32 G3 - final grade (numeric: from 0 to 20, output target)
+
+Additional note: there are several (382) students that belong to both datasets . 
+These students can be identified by searching for identical attributes
+that characterize each student, as shown in the annexed R file.