From dea0f4cdec5bdf24962c8ab3ab2a6473e202259a Mon Sep 17 00:00:00 2001
From: Charles <sircharlesaze@gmail.com>
Date: Sat, 25 Jan 2020 13:06:10 +0100
Subject: Custom statistics modulde, describe program

---
 src/analysis.py | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

(limited to 'src/analysis.py')

diff --git a/src/analysis.py b/src/analysis.py
index 64ba100..abc0ffb 100644
--- a/src/analysis.py
+++ b/src/analysis.py
@@ -1,10 +1,26 @@
-class Analysis(Dataset):
-    def __init__(self, path):
-        self.dataset_path = path
-        super().__init__(path)
+import numpy as np
+import pandas as pd
+
+import dslr_stat
 
-    def describe(self):
-        for title in self.df.
-        pass
 
+class Analysis:
+    def __init__(self, df):
+        self.df = df
 
+    def describe(self):
+        desc_df = pd.DataFrame(
+            dtype=np.float64,
+            columns=[c for c, t in zip(self.df.columns, self.df.dtypes) if t == np.float64],
+            index=['Count', 'Mean', 'Std', 'Min', '25%', '50%', '75%', 'Max']
+        )
+        for col in desc_df.columns:
+            desc_df.loc['Count', col] = len(self.df[col])
+            desc_df.loc['Mean', col] = dslr_stat.mean(self.df[col])
+            desc_df.loc['Std', col] = dslr_stat.std(self.df[col])
+            desc_df.loc['Min', col] = dslr_stat.min(self.df[col])
+            desc_df.loc['25%', col] = dslr_stat.q25(self.df[col])
+            desc_df.loc['50%', col] = dslr_stat.median(self.df[col])
+            desc_df.loc['75%', col] = dslr_stat.q75(self.df[col])
+            desc_df.loc['Max', col] = dslr_stat.max(self.df[col])
+        print(desc_df)
-- 
cgit