Program 1 import pandas as pd from sklearn.datasets import load_digits import matplotlib.pyplot as plt digits=load_digits() digits dir(digits) digits.target digits.data plt.gray() plt.matshow(digits.images[4]) plt.show() for i in range(5): plt.matshow(digits.images[i]) digits.target digits.target[:4] # Data Frame df=pd.DataFrame(digits.data) df.head()...
Program 1 import pandas as pd import numpy as np from sklearn import tree from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split df_titanic=pd.read_csv(“D://scikit_data/titanicData/titanic.csv”) df_titanic df_titanic.shape df_titanic.info() # Find Missing values df_titanic.isnull().sum() df_titanic=df_titanic.dropna() df_titanic.isnull().sum() df_titanic.shape...
Program 1 # Libraries import pandas as pd import numpy as np from sklearn import tree from sklearn.preprocessing import LabelEncoder df_titanic=pd.read_csv(“D://scikit_data/titanicData/titanic.csv”) df_titanic df_titanic.shape df_titanic.info() df_titanic.isnull().sum() df_titanic=df_titanic.dropna() df_titanic.isnull().sum() df_titanic.shape df_titanic.head() # Encoding le=LabelEncoder() df_titanic[‘Sex_new’]=le.fit_transform(df_titanic[‘Sex’]) df_titanic...
Program 1 import pandas as pd import numpy as np from sklearn import tree from sklearn.preprocessing import LabelEncoder df_tennis=pd.read_csv(“D://scikit_data/tennisData/tennis.csv”) df_tennis df_tennis.shape df_tennis.info() df_tennis.isnull().sum() df_tennis # Label Encoding le=LabelEncoder() df_tennis[‘outlook_new’]=le.fit_transform(df_tennis[‘outlook’]) df_tennis[‘temp_new’]=le.fit_transform(df_tennis[‘temp’]) df_tennis[‘humidity_new’]=le.fit_transform(df_tennis[‘humidity’]) df_tennis[‘windy_new’]=le.fit_transform(df_tennis[‘windy’]) df_tennis[‘play_new’]=le.fit_transform(df_tennis[‘play’]) df_tennis...
Program 1 import pandas as pd import numpy as np from sklearn import tree from sklearn.preprocessing import LabelEncoder from sklearn.model_selection import train_test_split df_iris=pd.read_csv(“D://scikit_data/IrisData/Iris.csv”) df_iris df_iris.shape df_iris.info() df_iris.isnull().sum() df_iris le=LabelEncoder() df_iris[‘Species_new’]=le.fit_transform(df_iris[‘Species’]) df_iris df_iris=df_iris.drop(‘Species’,axis=’columns’) df_iris df_iris=df_iris.drop(‘Id’,axis=’columns’)...
Program 1 import pandas as pd import numpy as np df_salary=df_salary=pd.read_csv(“D://scikit_data/tree/salaries.csv”) df_salary.head() df_salary.shape df_salary.isnull().sum() # Independed Columns df_input=df_salary.drop(‘salary_more_then_100k’,axis=’columns’) df_input #Depended Columns df_output=df_salary[‘salary_more_then_100k’] df_output from sklearn.preprocessing import LabelEncoder lb_company=LabelEncoder() lb_job=LabelEncoder() lb_degree=LabelEncoder() df_input[‘company_new’]=lb_company.fit_transform(df_input[‘company’]) df_input df_input[‘job_new’]=lb_job.fit_transform(df_input[‘job’]) df_input[‘degree_new’]=lb_job.fit_transform(df_input[‘degree’])...
Program 1 # Scatter Plot Demo| import pandas as pd import numpy as np import seaborn as sns import matplotlib.pyplot as plt df_titanic=sns.load_dataset(‘titanic’) df_titanic.head() df_titanic.info() df_titanic.shape df_titanic.isnull().sum() sns.scatterplot(x=’age’,y=’fare’,data=df_titanic) sns.scatterplot(x=’age’,y=’fare’,hue=’sex’,data=df_titanic) sns.scatterplot(x=’age’,y=’fare’,hue=’sex’,style=’who’,data=df_titanic) plt.figure(figsize=(15,10)) sns.scatterplot(x=’age’,y=’fare’,hue=’sex’,style=’who’,size=’who’,data=df_titanic) plt.figure(figsize=(15,10)) sns.scatterplot(x=’age’,y=’fare’,hue=’sex’,style=’who’,size=’who’,sizes=(100,500),data=df_titanic)...
Program 1 import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns ar_2d=np.linspace(1,5,12).reshape(4,3) ar_2d sns.heatmap(ar_2d) df_global=pd.read_csv(“D://scikit_data/global/global_warming.csv”) df_global.info() df_global.shape df_global=df_global.drop(columns=[‘Country Code’,’Indicator Name’,’Indicator Code’],axis=’columns’) df_global.head() df_global=df_global.set_index(‘Country Name’) df_global sns.heatmap(df_global) sns.heatmap(df_global,vmin=0,vmax=25)...
Program 1 # ecdf= Empirical Cumulative Distribution Function plot import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns df_value=pd.read_csv(“D://scikit_data/Billing/data.csv”) df_value sns.set_style(‘darkgrid’) sns.ecdfplot(x=’value’,data=df_value) df_tips=pd.read_csv(“D://scikit_data/Billing/tips.csv”) df_tips df_tips[‘tip’].head() sns.ecdfplot(x=’tip’,data=df_tips) df_tips.tip.max()...
Program 1 import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns df_tips=pd.read_csv(“D://scikit_data/Billing/tips.csv”) df_tips.head() df_tips.shape df_tips.isnull().sum() df_tips.info() sns.displot(x=’total_bill’,data=df_tips) sns.displot(x=’total_bill’,data=df_tips,bins=100) sns.displot(x=’total_bill’,data=df_tips) sns.displot(x=’total_bill’,data=df_tips,kind=’hist’) # # kde=Karnel Denstity Estimeter sns.displot(x=’total_bill’,data=df_tips,kind=’kde’) #ecdf=...
