Blog

i am not able to blog due to highly packed intern.

import pandas as pd

## Series: (1-dimensional)

series=pd.Series(["Jigyasu","Mayank","Pankaj","Suraj","Hardik","Saurabh"])

series

series_1=pd.Series(["Black","Pink","White","Red","Green","Blue"])

series_1

## DataFrame: (2-dimensional)

fav_color=pd.DataFrame({"Name":series,"Fav. Color":series_1})
fav_color

## Import data

Car_Data=pd.read_csv("car-sales.csv")

Car_Data

## Exporting Dataframe

Car_Data.to_csv("Exported_Car_Data",index=False)

Ex_Car_Data=pd.read_csv("Exported_Car_Data")
Ex_Car_Data

## Describing Data

# Attributes
Car_Data.dtypes

Car_Data.columns

Car_Column=Car_Data.columns
Car_Column

Car_Data.index

Car_Data.describe()

Car_Data.info()

Car_Data.sum()

Car_Data["Odometer (KM)"].mean()

Car_Data["Odometer (KM)"].sum()

len(Car_Data)

## Selection and viewing

Car_Data.head()

Car_Data.head(7)

Car_Data.tail()

Car_Data.tail(3)

Car_Data.loc[3]

iloc: actual index return

Car_Data.iloc[:3]

Car_Data.loc[:3]

Car_Data["Make"]

Car_Data.Make

Car_Data[Car_Data["Make"]=="Toyota"]

Car_Data[Car_Data["Odometer (KM)"]>=50000]

Car_Data

pd.crosstab(Car_Data["Make"],Car_Data["Doors"])

Car_Data["Odometer (KM)"].mean()

Car_Data["Odometer (KM)"].plot()

Car_Data["Odometer (KM)"].hist()

Car_Data["Price"].plot()



Car_Data

Car_Data["Price"]

Car_Data["Price"] = Car_Data["Price"].str.replace('[\$,]', '', regex=True).astype(float)

Car_Data

Car_Data["Price"].plot()

Car_Data["Price"].hist()

## Manipulating Data

Car_Data["Make"].str.lower()

Car_Data["Make"]=Car_Data["Make"].str.upper()

Car_Data

Car_Data["Colour"]=Car_Data["Colour"].str.lower()
Car_Data

Car_Data_Missing=pd.read_csv("car-sales-missing-data.csv")
Car_Data_Missing

Car_Data_Missing["Odometer"].mean()

Car_Data_Missing

Car_Data_Missing.dropna(inplace=True)
Car_Data_Missing

Car_Data

series=pd.Series([5,5,4,5,6,4,5,4])

series

Car_Data["Seats"]=series

Car_Data

Car_Data["Seats"].fillna(Car_Data["Seats"].mean(),inplace=True)

Car_Data

li=[4.2,5.6,4.9,7.5,6.4,8.2]
Car_Data["Milage"]=li
Car_Data

pd series need to have same arguments as data table but python list must have 

li=[4.2,5.6,4.9,7.5,6.4,8.2,7.5,6.4,5.0,10.9]
Car_Data["Milage"]=li
Car_Data

Car_Data["Fuel Used"]=Car_Data["Odometer (KM)"]/Car_Data["Milage"]
Car_Data

Car_Data["No. of wheels"]=4
Car_Data

Car_Data["Pollution Reciept"]=True
Car_Data

Car_Data["Sample"]="Has to remove"
Car_Data

Car_Data.drop("Sample",axis=1,inplace=True)

Car_Data

Car_Data_Shuffled=Car_Data.sample(frac=1)
Car_Data_Shuffled

Insurance=pd.read_csv("Student insurance E-card details. (2).csv")
Insurance.head()

Insurance

Insurance_Random=Insurance.sample(frac=1)

Insurance_Random

Insurance_Random.to_csv("Insurance_Random")

Insurance.sample(frac=0.03)

Insurance_Random.reset_index()

Insurance_Random.reset_index(drop=True)

Car_Data

Car_Data["Odometer (KM)"]=Car_Data["Odometer (KM)"].apply(lambda x:x/1.6)
Car_Data

ML Process includes Problem to be solved, Data analysis, Evaluation of data, Features according to problem, Modelling model, Experimentation of Model for new values.

Also, I’m going to learn Python. Till strings it’s easy !

Machine Learning is a way or method to train machine (computer) to predict answers using a chunk of data. Modeling a machine according to query statement, collecting and arranging data, lies under machine learning process.