Atividade - Pandas

exercicios/para-casa/AtvCasa.py

@@ -0,0 +1,28 @@
+import pandas as pd
+
+df = pd.read_csv("C:/Users/thai/Downloads/reprograma/on33-python-s09-pandas-numpy-I/material/mais_ouvidas_2024.csv")
+
+#print(df.head())
+#print (df.columns)
+#print(df.dtypes)
+
+to_parse = ['All Time Rank', 'Spotify Streams', 'Spotify Playlist Count', 'Spotify Playlist Reach', 'YouTube Views', 'YouTube Likes', 'TikTok Posts', 'TikTok Likes',
+            'TikTok Views', 'YouTube Playlist Reach', 'Deezer Playlist Reach', 'Pandora Streams', 'Pandora Track Stations', 'Soundcloud Streams', 'Shazam Counts']
+
+for column in to_parse:
+    df[column] = df[column].str.replace(",", "").astype(float)
+
+
+df['Release Date'] = pd.to_datetime((df['Release Date']), format="%m/%d/%Y")
+
+df['Total Streaming'] = df[['Spotify Streams', 'YouTube Views', 'TikTok Views', 'Pandora Streams', 'Soundcloud Streams']].sum(axis=1)
+print(df['Total Streaming'].head())
+
+filtered_df = df[(df['Spotify Popularity'] > 80) & (df['Total Streaming'] > 1_000_000)]
+print(filtered_df.head())
+
+
+df.to_json("../musicas_populares.json", index=False)
+
+
+

exercicios/para-sala/ETL_pandas.py

@@ -1,3 +1,31 @@
+<<<<<<< HEAD
+import pandas as pd 
+
+##['TransactionID', 'Date', 'MobileModel', 'Brand', 'Price', 'UnitsSold','TotalRevenue', 'CustomerAge', 'CustomerGender', 'Location','PaymentMethod']
+
+df = pd.read_csv(
+    "C:/Users/thai/Downloads/reprograma/on33-python-s09-pandas-numpy-I/material/mobile_sales.csv"
+)
+
+print(df.head(n=10))#Traz as 10 primeiras linhas do arquivo
+print(df.columns)
+df_valores_nulos = df.isnull() #identifica valores nulos
+print(df_valores_nulos.sum())
+print(df.duplicated()) #identificar valores duplicados
+
+df['Date'] = pd.to_datetime(df['Date'], format="mixed")
+
+df["Total Sales Value"] = df["Price"] * df["UnitsSold"] # Cria uma nova coluna com o título Total Sales Value através do produto de Price x UnitsSold 
+print(df["Total Sales Value"]) # print a nova coluna
+print(df.columns)
+df["Profit Margin"] = (df["Price"] * 0.30) * df["UnitsSold"] 
+print(df["Profit Margin"]) # print a nova coluna
+print(df.columns)
+
+#Filtragem
+filtered_df = df [(df["Total Sales Value"] > 100_000) & (df["Profit Margin"] > 20_000)]
+print(filtered_df)
+=======
 import pandas as pd
 
 # ['TransactionID', 'Date', 'MobileModel', 'Brand', 'Price', 'UnitsSold','TotalRevenue', 'CustomerAge', 'CustomerGender', 'Location','PaymentMethod']
@@ -28,3 +56,4 @@
 print(filtered_df.head())
 
 filtered_df.to_csv("./exercicios/para-sala/filtered_list.csv", index=False)
+>>>>>>> d945731276aa7dccf62e91cd8b5e6b8d11577dbf