Coursera

The Association between GDP Per Capita and Various Development Indicators

Results Descriptive Statistics Table 1 shows descriptive statistics for GDP per capita and the quantitative predictors. The average GDP per capita was US$ 14,751 (std dev = 21,612) with a minimum GDP of US$ 244.2 and a maximum of US$ 149,161

Bivariate Analyses: Scatter plots for the association between the GDP per capita response variable and the quantitative predictors (Figure 1) revealed that GDP per capita has the strongest correlation with the rate of fixed broadband subscriptions (Pearson r = 0.789, p < .0001). All correlations are shown in Table 2.

Note that the Under 5 Mortality Rate was transformed to a logarithmic scale in order to linearize it for more accurate regression analysis. Figure 2 shows the scatterplot resulting from this transformation, showing the increased linearity.

Lasso Regression Analysis: Of the 8 predictor variables analyzed, the lasso regression model dropped 2 of them. The proportion of women in national parliament was not retained (the regression analysis also showed it to have the least significance by a wide margin), and the rural population rate was not retained (the urban population rate captures the same information, in the inverse, and also had a slightly higher correlation than the rural population rate; the urban population rate was retained). Table 3 shows the regression coefficients of the lasso analysis.

The Association between GDP Per Capita and Various Development Indicators

Methods

Sample: The World Bank data set is a subset of data extracted from the primary World Bank collection of development indicators, compiled from officially-recognized international sources, from the years 2012 and 2013. The sample used in this study contained N = 248 countries with data aggregated from national, regional, and global estimates. Although all variables have valid data observations for a minimum of 190 countries, only data from the year 2012 was used in this study because this was not intended to be a longitudinal study. Furthermore, 2013 data has been reserved to test the regression equation developed by the 2012 data for validity. 

The Association between GDP Per Capita and Various Development Indicators

Introduction to the Research Question: 

THE MOVIE DATASET.

TASK- IS to check which cluster perform best and to check and compare the statistics of each cluster( Ratings, Revenue, Votes , Budget, Average Vote count, Movie Title and Popularity)

#Check if rows contain any null values data_numeric.isnull().sum()

# -*- coding: utf-8 -*-

from pandas import Series, DataFrame import pandas as pd import numpy as np import matplotlib.pylab as plt from sklearn.cross_validation import train_test_split from sklearn import preprocessing from sklearn.cluster import KMeans

#

Read the movies metadata csv file

“”“ Data Management ”“” data = pd.read_csv(“movies_metadata.csv”)

#upper-case all DataFrame column names

data.columns = map(str.upper, data.columns)

#Only keep the numeric columns for our analysis. However, we’ll keep titles also #to interpret the results at the end of clustering. Note that this title column will #not be used in the analysis.

data.drop(data.index[19730],inplace=True) data.drop(data.index[29502],inplace=True) data.drop(data.index[35585],inplace=True)

data.columns

data_numeric = data[[‘BUDGET’,'POPULARITY’,'REVENUE’,'RUNTIME’,'VOTE_AVERAGE’,'VOTE_COUNT’,'TITLE’]]

data_numeric.head()

#Check if rows contain any null values

data_numeric.isnull().sum()

# Data Management #Drop all the rows with null values

data_clean = data_numeric.dropna()

# subset clustering variables cluster=data_clean cluster.describe()

#Let’s see the statistics for the votes counts for the movies data cluster['VOTE_COUNT’].describe()

#We see that a half of movies have been rated less than 10 times. For easier interpretability,

#let’s take only the movies that have more than 30 votes, i.e. top 26% of the movies.

cluster['VOTE_COUNT’].quantile(np.arange(.74,1,0.01))

cluster = cluster[cluster['VOTE_COUNT’]>30]

cluster.shape

cluster.columns

# standardize clustering variables to have mean=0 and sd=1 #Data Normalization

clustervar=cluster.copy() clustervar = clustervar.drop(columns='TITLE’) clustervar['BUDGET’]=preprocessing.scale(clustervar['BUDGET’].astype('float64’)) clustervar['POPULARITY’]=preprocessing.scale(clustervar['POPULARITY’].astype('float64’)) clustervar['REVENUE’]=preprocessing.scale(clustervar['REVENUE’].astype('float64’)) clustervar['RUNTIME’]=preprocessing.scale(clustervar['RUNTIME’].astype('float64’)) clustervar['VOTE_AVERAGE’]=preprocessing.scale(clustervar['VOTE_AVERAGE’].astype('float64’)) clustervar['VOTE_COUNT’]=preprocessing.scale(clustervar['VOTE_COUNT’].astype('float64’))

clustervar.head()

Apply K-Means Clustering

What k to choose?

Let’s fit cluster size 1 to 20 on our data and take a look at the corresponding score value.                                                          

from scipy.spatial.distance import cdist clusters=range(1,20) meandist=[]

for k in clusters:   model=KMeans(n_clusters=k)   model.fit(clustervar)   clusassign=model.predict(clustervar)   meandist.append(sum(np.min(cdist(clustervar, model.cluster_centers_, 'euclidean’), axis=1))   / clus_train.shape[0])

These MeanDist signify how far our observations are from the cluster center. A large positive or a large negative value would indicate that the cluster center is far from the observations.

Based on these MeanDist, we plot an Elbow curve to decide which cluster size is optimal. Note that we are dealing with tradeoff between cluster size(hence the computation required) and the relative accuracy.

“”“

Plot average distance from observations from the cluster centroid to use the Elbow Method to identify number of clusters to choose ”“”

plt.plot(clusters, meandist) plt.xlabel('Number of clusters’) plt.ylabel('Average distance’) plt.title('Selecting k with the Elbow Method’)

Our Elbow point is around cluster size of 5. We will use k=5 to further interpret our clustering result.

# Interpret 5 cluster solution

model3=KMeans(n_clusters=5) model3.fit(clustervar) clusassign=model3.predict(clustervar)

# plot clusters

from sklearn.decomposition import PCA pca_2 = PCA(2) plot_columns = pca_2.fit_transform(clustervar) plt.scatter(x=plot_columns[:,0], y=plot_columns[:,1], c=model3.labels_,) plt.xlabel('Canonical variable 1’) plt.ylabel('Canonical variable 2’) plt.title('Scatterplot of Canonical Variables for 3 Clusters’) plt.show()

As a result of clustering, we have the clustering label. Let’s put these labels back into the original numeric data frame.

len(model3.labels_)

cluster['cluster’] = model3.labels_

cluster.head()

Interpret clustering results

#Let’s see cluster sizes first.

import seaborn as sns plt.figure(figsize=(12,7)) axis = sns.barplot(x=np.arange(0,5,1),y=cluster.groupby(['cluster’]).count()['BUDGET’].values) x=axis.set_xlabel(“Cluster Number”) x=axis.set_ylabel(“Number of movies”)

We clearly see that one cluster is the largest and one cluster has the fewest number of movies.

Let’s look at the cluster statistics.

cluster.groupby(['cluster’]).mean()

We see that one cluster which is also the smallest, is the cluster of movies that received maximum number of votes(in terms of counts) and also have very high popularity and total runtime and net revenue. Let’s see some of the movies that belong to this cluster.

size_array = list(cluster.groupby(['cluster’]).count()['BUDGET’].values)

cluster[cluster['cluster’]==size_array.index(sorted(size_array)[0])].sample(5)

We see many big movie names in this cluster. So the results are intuitive.

Cluster that is the second smallest cluster in the results, has 2nd highest votes count and the most highly rated movies.

The runtime for these movies is on the higher end and popularity score is also good.

Let’s see some of the movie names from this cluster.

cluster[cluster['cluster’]==size_array.index(sorted(size_array)[1])].sample(5)

Lastly, let’s take a look at the least successful movies. This cluster represents the movies that received least number of votes and also has the smallest run-time, revenue and popularity score.

cluster[cluster['cluster’]==size_array.index(sorted(size_array)[-1])].sample(5)

A lasso regression analysis was conducted to identify a subset of variables from a pool of 23 categorical and quantitative predictor variables that best predicted a quantitative response variable measuring edibility of mushroom. The following variables with their coding were used for the prediction of mushroom edibility:   ‘cap-shape’: 0.006830438130309507, 'cap-surface’: 0.029933766629635882, 'cap-color’: -0.022465617329256313, 'bruises%3F’: 0.04793775721081437, 'odor’: -0.060433929659676894, 'gill-attachment’: -0.10013577023198816, 'gill-spacing’: -0.1622243103092139, 'gill-size’: 0.26331100160882526, 'gill-color’: 0.010083513903480262, 'stalk-shape’: -0.07950868810658265, 'stalk-root’: -0.13261223526361968, 'stalk-surface-above-ring’: -0.07914091048443232, 'stalk-surface-below-ring’: -0.0373198000983224, 'stalk-color-above-ring’: -0.012064278978042246, 'stalk-color-below-ring’: 0.0020354486823514722, 'veil-type’: 0.0, 'veil-color’: 0.03055062600401165, 'ring-number’: 0.09701363270357884, 'ring-type’: -0.20784377127141931, 'spore-print-color’: -0.1851868692914453, 'population’: -0.04230101335363859, 'habitat’: 0.0172138424148384}  All predictor variables were standardized to have a mean of zero and a standard deviation of one.

I used lasso regression to generate a model to predict mushroom edibility based on their feasures, the coefficients of each feature is shown below:

{‘cap-shape’: 0.006830438130309507, 'cap-surface’: 0.029933766629635882, 'cap-color’: -0.022465617329256313, 'bruises%3F’: 0.04793775721081437, 'odor’: -0.060433929659676894, 'gill-attachment’: -0.10013577023198816, 'gill-spacing’: -0.1622243103092139, 'gill-size’: 0.26331100160882526, 'gill-color’: 0.010083513903480262, 'stalk-shape’: -0.07950868810658265, 'stalk-root’: -0.13261223526361968, 'stalk-surface-above-ring’: -0.07914091048443232, 'stalk-surface-below-ring’: -0.0373198000983224, 'stalk-color-above-ring’: -0.012064278978042246, 'stalk-color-below-ring’: 0.0020354486823514722, 'veil-type’: 0.0, 'veil-color’: 0.03055062600401165, 'ring-number’: 0.09701363270357884, 'ring-type’: -0.20784377127141931, 'spore-print-color’: -0.1851868692914453, 'population’: -0.04230101335363859, 'habitat’: 0.0172138424148384}

MSE is shown below:

training data MSE 0.051799015501909046 test data MSE 0.05872418476904985 training data R-square 0.7804775315498513 test data R-square 0.7515249302439275

###########################CODE###########################

# -*- coding: utf-8 -*- “”“ Created on Mon Dec 14 16:26:46 2015

@author: jrose01 ”“”

#from pandas import Series, DataFrame import pandas as pd import numpy as np import matplotlib.pylab as plt from sklearn.cross_validation import train_test_split from sklearn.linear_model import LassoLarsCV import os from sklearn import preprocessing

os.chdir(r"C:\Users\jliu65\Desktop\ML\Course_1_1\Week1")

#Load the dataset data = pd.read_csv(“mushroom.csv”)

# Data Management data_clean = data.dropna() le = preprocessing.LabelEncoder() data_clean = data_clean.apply(le.fit_transform)

#select predictor variables and target variable as separate data sets predvar= data_clean[['cap-shape’,'cap-surface’,'cap-color’,'bruises%3F’,'odor’,'gill-attachment’,'gill-spacing’,'gill-size’,'gill-color’,'stalk-shape’,'stalk-root’,'stalk-surface-above-ring’,'stalk-surface-below-ring’,'stalk-color-above-ring’,'stalk-color-below-ring’,'veil-type’,'veil-color’,'ring-number’,'ring-type’,'spore-print-color’,'population’,'habitat’]]

target = data_clean['class’]

# standardize predictors to have mean=0 and sd=1 predictors=predvar.copy() from sklearn import preprocessing predictors['cap-shape’]=preprocessing.scale(predictors['cap-shape’].astype('float64’)) predictors['cap-surface’]=preprocessing.scale(predictors['cap-surface’].astype('float64’)) predictors['cap-color’]=preprocessing.scale(predictors['cap-color’].astype('float64’)) predictors['bruises%3F’]=preprocessing.scale(predictors['bruises%3F’].astype('float64’)) predictors['odor’]=preprocessing.scale(predictors['odor’].astype('float64’)) predictors['gill-attachment’]=preprocessing.scale(predictors['gill-attachment’].astype('float64’)) predictors['gill-spacing’]=preprocessing.scale(predictors['gill-spacing’].astype('float64’)) predictors['gill-size’]=preprocessing.scale(predictors['gill-size’].astype('float64’)) predictors['gill-color’]=preprocessing.scale(predictors['gill-color’].astype('float64’)) predictors['stalk-shape’]=preprocessing.scale(predictors['stalk-shape’].astype('float64’)) predictors['stalk-root’]=preprocessing.scale(predictors['stalk-root’].astype('float64’)) predictors['stalk-surface-above-ring’]=preprocessing.scale(predictors['stalk-surface-above-ring’].astype('float64’)) predictors['stalk-surface-below-ring’]=preprocessing.scale(predictors['stalk-surface-below-ring’].astype('float64’)) predictors['stalk-color-above-ring’]=preprocessing.scale(predictors['stalk-color-above-ring’].astype('float64’)) predictors['stalk-color-below-ring’]=preprocessing.scale(predictors['stalk-color-below-ring’].astype('float64’)) predictors['veil-type’]=preprocessing.scale(predictors['veil-type’].astype('float64’)) predictors['veil-color’]=preprocessing.scale(predictors['veil-color’].astype('float64’)) predictors['ring-number’]=preprocessing.scale(predictors['ring-number’].astype('float64’)) predictors['ring-type’]=preprocessing.scale(predictors['ring-type’].astype('float64’)) predictors['spore-print-color’]=preprocessing.scale(predictors['spore-print-color’].astype('float64’)) predictors['population’]=preprocessing.scale(predictors['population’].astype('float64’)) predictors['habitat’]=preprocessing.scale(predictors['habitat’].astype('float64’))

# split data into train and test sets pred_train, pred_test, tar_train, tar_test = train_test_split(predictors, target,                                                             test_size=.3, random_state=123)

# specify the lasso regression model model=LassoLarsCV(cv=10, precompute=False).fit(pred_train,tar_train)

# print variable names and regression coefficients print(dict(zip(predictors.columns, model.coef_)))

# plot coefficient progression m_log_alphas = -np.log10(model.alphas_) ax = plt.gca() plt.plot(m_log_alphas, model.coef_path_.T) plt.axvline(-np.log10(model.alpha_), linestyle=’–’, color='k’,           label='alpha CV’) plt.ylabel('Regression Coefficients’) plt.xlabel(’-log(alpha)’) plt.title('Regression Coefficients Progression for Lasso Paths’)

# plot mean square error for each fold m_log_alphascv = -np.log10(model.cv_alphas_) plt.figure() plt.plot(m_log_alphascv, model.cv_mse_path_, ’:’) plt.plot(m_log_alphascv, model.cv_mse_path_.mean(axis=-1), 'k’,        label='Average across the folds’, linewidth=2) plt.axvline(-np.log10(model.alpha_), linestyle=’–’, color='k’,           label='alpha CV’) plt.legend() plt.xlabel(’-log(alpha)’) plt.ylabel('Mean squared error’) plt.title('Mean squared error on each fold’)

# MSE from training and test data from sklearn.metrics import mean_squared_error train_error = mean_squared_error(tar_train, model.predict(pred_train)) test_error = mean_squared_error(tar_test, model.predict(pred_test)) print ('training data MSE’) print(train_error) print ('test data MSE’) print(test_error)

# R-square from training and test data rsquared_train=model.score(pred_train,tar_train) rsquared_test=model.score(pred_test,tar_test) print ('training data R-square’) print(rsquared_train) print ('test data R-square’) print(rsquared_test)

Interpretation:

Introduction and Dataset description:

Random forest analysis was performed to evaluate the importance of a series of explanatory variables in predicting a binary, categorical response variable. The following explanatory variables were included as possible contributors to a random forest evaluating odor (my response variable), stem root, stalk root, color, ring type, veil color, stalk-color below the ring, 

I downloaded one big dataset about the edibility of mushrooms based on their properties, e.g. their size, color, and smell etc. Then I used Random Tree Forests method for training the model.

Python Syntax and Output:

The confusion matrix is

[[1353    0] [   0  905]] the accuracy score is 100%.

The feature importance score is as follows:

[0.00574359 0.00725241 0.01656165 0.03183099 0.13902492 0.0010708 0.02031286 0.07602323 0.02706282 0.19774726 0.04952499 0.0697341 0.04745347 0.00182847 0.01628367 0.         0.0007003  0.01219555 0.08216999 0.09301486 0.0122928  0.09217128]

By mirroring the score to corresponding features, I find out the ‘odor’, ‘stalk-root’, ‘ring type’ features play a more important roles for deciding the edibility of different kinds of mushrooms. While features like  edibility(response variable) cap-shape’,'cap-surface’,'cap-color’,'bruises%3F’,'odor’,'gill-attachment’,'gill-spacing’,'gill-size’,'gill-color’,'stalk-shape’,'stalk-root’,'stalk-surface-above-ring’,'stalk-surface-below-ring’,'stalk-color-above-ring’,'stalk-color-below-ring’,'veil-type’,'veil-color’,'ring-number’,'ring-type’,'spore-print-color’,'population’,'habitat ‘veil color’ and ‘stalk-color-below-ring’ play minor or seemingly no role in deciding the edibility of mushrooms.

#######################CODE###########################

from pandas import Series, DataFrame import pandas as pd import numpy as np import os import matplotlib.pylab as plt from sklearn.cross_validation import train_test_split from sklearn.tree import DecisionTreeClassifier from sklearn.metrics import classification_report import sklearn.metrics from sklearn import preprocessing # Feature Importance from sklearn import datasets from sklearn.ensemble import ExtraTreesClassifier

os.chdir(r"C:/Users/jliu65/Desktop/ML/Course_1_1/Week1/Assignment")

#Load the dataset

AH_data = pd.read_csv(“mushroom.csv”) data_clean = AH_data.dropna() le = preprocessing.LabelEncoder() data_clean = data_clean.apply(le.fit_transform)

data_clean.dtypes data_clean.describe()

#Split into training and testing sets

predictors = data_clean[[‘cap-shape’,'cap-surface’,'cap-color’,'bruises%3F’,'odor’,'gill-attachment’,'gill-spacing’,'gill-size’,'gill-color’,'stalk-shape’,'stalk-root’,'stalk-surface-above-ring’,'stalk-surface-below-ring’,'stalk-color-above-ring’,'stalk-color-below-ring’,'veil-type’,'veil-color’,'ring-number’,'ring-type’,'spore-print-color’,'population’,'habitat’]]

targets = data_clean['class’]

pred_train, pred_test, tar_train, tar_test  = train_test_split(predictors, targets, test_size=.4)

pred_train.shape pred_test.shape tar_train.shape tar_test.shape

#Build model on training data from sklearn.ensemble import RandomForestClassifier

classifier=RandomForestClassifier(n_estimators=50) classifier=classifier.fit(pred_train,tar_train)

predictions=classifier.predict(pred_test) #print(classifier.feature_importances_)

print(sklearn.metrics.confusion_matrix(tar_test,predictions)) print(sklearn.metrics.accuracy_score(tar_test, predictions))

# fit an Extra Trees model to the data model = ExtraTreesClassifier() model.fit(pred_train,tar_train) # display the relative importance of each attribute print(model.feature_importances_*100)

“”“ Running a different number of trees and see the effect of that on the accuracy of the prediction ”“”

trees=range(25) accuracy=np.zeros(25)

for idx in range(len(trees)):  classifier=RandomForestClassifier(n_estimators=idx + 1)  classifier=classifier.fit(pred_train,tar_train)  predictions=classifier.predict(pred_test)  accuracy[idx]=sklearn.metrics.accuracy_score(tar_test, predictions)

plt.cla() plt.plot(trees, accuracy)

Interpretation:

Dataset description:

I used Tree add health dataset provided by coursera. The following will explain you the python syntax , python output and confusion matrix.

Python syntax:

Python Output:

I used the decision tree to use 80% of the data for training the model and 20% of the data for testing.

The confusion matrix is

[[677   0] [  0 452]] the accuracy score is 100%.

Dataset Description:

The dataset contains variables - General life satisfaction score, food satisfaction score, age, gender, smoking status

Qualitative variables: Gender, Smoking status

Quantitative variables: General life satisfaction score, food satisfaction score, age

Python Code syntax:

Output:

Logit Regression Results                          

======================================================================

Dep. Variable:         Smoking_status   No. Observations:                   19 Model:                          Logit   Df Residuals:                       17 Method:                           MLE   Df Model:                            1 Date:                Mon, 28 Jan 2019   Pseudo R-squ.:                 0.02308 Time:                        12:14:55   Log-Likelihood:                -12.216 converged:                       True   LL-Null:                       -12.504                                        LLR p-value:                    0.4475 ===========================================================================================                              coef    std err          z      P>|z|      [0.025      0.975] ------------------------------------------------------------------------------------------- Intercept                  -2.6667      4.347     -0.614      0.540     -11.186       5.852 Food_satisfaction_score     0.2340      0.317      0.737      0.461      -0.388       0.856 ===========================================================================================                         Lower CI    Upper CI        OR Intercept                0.000014  348.082744  0.069479 Food_satisfaction_score  0.678281    2.354006  1.263598

Results and Interpretation:

1.Dataset description:

The dataset contains variables - General Life satisfaction score, Food Satisfaction score, Age, Smoking status, and gender.

Quantitative variables: General life satisfaction score, Food Satisfaction score, Age

Qualitative variables: Smoking status, gender.

2.Python Syntax to perform analysis:

3. Output:

OLS Regression Results                                   =========================================================================================== Dep. Variable:     General_Life_satisfaction_score   R-squared:                       0.244 Model:                                         OLS   Adj. R-squared:                  0.149 Method:                              Least Squares   F-statistic:                     2.581 Date:                             Mon, 28 Jan 2019   Prob (F-statistic):              0.107 Time:                                     09:38:03   Log-Likelihood:                -27.322 No. Observations:                               19   AIC:                             60.64 Df Residuals:                                   16   BIC:                             63.48 Df Model:                                        2                                         Covariance Type:                         nonrobust                                         ===========================================================================================                              coef    std err          t      P>|t|      [0.025      0.975] ------------------------------------------------------------------------------------------- Intercept                   8.3533      2.200      3.798      0.002       3.690      13.016 Smoking_status             -1.1392      0.536     -2.125      0.050      -2.276      -0.003 Food_satisfaction_score    -0.0689      0.161     -0.428      0.674      -0.410       0.272 ============================================================================== Omnibus:                        1.633   Durbin-Watson:                   1.852 Prob(Omnibus):                  0.442   Jarque-Bera (JB):                1.144 Skew:                           0.344   Prob(JB):                        0.565 Kurtosis:                       2.015   Cond. No.                         121. ==============================================================================



4.Results and Interpretation:

Test a Basic Linear Regression Model

Dataset description:

The dataset contains variables General life satisfaction score, age, smoking status, and gender.

Quantitative variables: General life satisfaction score and Age

Qualitative variables: Smoking status(0- No smoking, 1- smoking), Gender(0=Male, 1=Female)

Python syntax to perform the analysis:

The python syntax used for analysis is shown through the following screenshot.

Output:

The following shows us the output which has arrived performing the above code for regression analysis:

Freq1 = data['Smoking_status'].value_counts(sort=False, dropna=False) print (Freq1)

0     7 1    12

(0- Non-smoker, 1- Smoker) Name: Smoking_status, dtype: int64

                                 OLS Regression Results                                   =========================================================================================== Dep. Variable:     General_Life_satisfaction_score   R-squared:                       0.235 Model:                                         OLS   Adj. R-squared:                  0.190 Method:                              Least Squares   F-statistic:                     5.229 Date:                             Wed, 09 Jan 2019   Prob (F-statistic):             0.0353 Time:                                     14:39:07   Log-Likelihood:                -27.430 No. Observations:                               19   AIC:                             58.86 Df Residuals:                                   17   BIC:                             60.75 Df Model:                                        1                                         Covariance Type:                         nonrobust                                         ==================================================================================                     coef    std err          t      P>|t|      [0.025      0.975] ---------------------------------------------------------------------------------- Intercept          7.4286      0.410     18.136      0.000       6.564       8.293 Smoking_status    -1.1786      0.515     -2.287      0.035      -2.266      -0.091 ============================================================================== Omnibus:                        2.013   Durbin-Watson:                   1.802 Prob(Omnibus):                  0.365   Jarque-Bera (JB):                1.148 Skew:                           0.255   Prob(JB):                        0.563 Kurtosis:                       1.910   Cond. No.                         3.06 ==============================================================================

Results and interpretation:

The results of the linear regression model indicated that smoking (Beta=-1.17, p=.003) was significantly and negatively associated with general life satisfaction score.

Writing about your data:

Sample:

The sample is from a questionnaire-based survey that was collected during my post-graduation on Health-related Quality of Life, and other sociodemographic characteristics. Participants(n=165) represented the children from various part of the Indian country registered to the thalassemia treatment center and included children suffering from thalassemia major and excluded children suffering from other chronic diseases. The entire sample is included in the data analysis (n=165).

Procedure:

Data were collected by me who acted as at principal investigator during 2017-18 through the questionnaire-based survey. All children were selected in the particular thalassemia treatment center following the approval from Institutional ethics committee from that institution and informed consent procedures approved from parents of the children.

Measures:

Dataset:

The dataset contains variables like life satisfaction score, food satisfaction score, income.

Aim:

To check the moderating effect of the income variable in the association between general life satisfaction and food satisfaction.

Python code Syntax:

Python Output:

association between Food satisfaction and Life satisfaction for LOW income persons (-0.16666666666666666, 0.7887799817897356)

association between Food satisfaction and Life satisfaction for MIDDLE income persons (0.9707253433941508, 0.15442095831126684)

association between Food satisfaction and Life satisfaction for HIGH income persons (-0.37241359182061873, 0.2593587449924706)



Interpretation:

The income variable does not have a relationship between the association between life satisfaction score and food satisfaction score.

Description of Dataset:

The dataset contains variables like food satisfaction score, general life satisfaction score.

Aim: 

To find the strength of the relationship between food satisfaction score and general life satisfaction score.

Python Syntax:

Python Output:

Pearson Correlation of Food Satisfaction score and Life satisfaction score Out[14]: (-0.1748367339531579, 0.47405240335740717)

Interpretation:

The scatterplot indicates a downwards slope which suggests a negative relationship between the two variables.

There is a negative relationship between food satisfaction score and general life satisfaction score (-0.174), which is not statistically significant as the p-value is greater than 0.05.

The Dataset contains variables of Food satisfaction and ethnicity (people classified through their Ethnicity )

Aim: 

To examine the relationship of food satisfaction with different ethnic group origin people.

Python Syntax:

Python Output:

Ethinicity               1  2  3  4  5 Food_satisfaction_score               12                       1  1  0  1  2 13                       0  1  1  2  1 14                       0  2  1  0  0 15                       0  1  2  0  0 16                       0  0  1  0  0 17                       1  0  0  1  0 Chisquare value,             p value,                         expected counts (  19.855,             0.46703243053045784,        20, array([[0.52631579, 1.31578947, 1.31578947, 1.05263158, 0.78947368],       [0.52631579, 1.31578947, 1.31578947, 1.05263158, 0.78947368],       [0.31578947, 0.78947368, 0.78947368, 0.63157895, 0.47368421],       [0.31578947, 0.78947368, 0.78947368, 0.63157895, 0.47368421],       [0.10526316, 0.26315789, 0.26315789, 0.21052632, 0.15789474],       [0.21052632, 0.52631579, 0.52631579, 0.42105263, 0.31578947]]))

Bar graph of Food satisfaction and Ethnicity:

Interpretation:

As p-value (0.467) greater than 0.05, there exists no relationship between the food satisfaction score and ethnicity group people. 

The bar diagram also shows that there is no increasing or decreasing trend in the graph which further suggests no relationship between the two variables.

Introduction to my dataset:

My dataset contains Food satisfaction score, General Life satisfaction score, gender, age, and ethnicity.

Here, I have used Ethnicity as the Categorical Explanatory variable and General Life satisfaction score as the Quantitative  Response variable.

Null Hypothesis: The mean General Life satisfaction score among all ethnic groups are same.

Alternate Hypothesis: Not all the mean General Life satisfaction score among all ethnic groups are same.

SYNTAX(Input) file for the Anova Test:

The following picture shows the input file or syntax file that I used for the execution of Anova test and post-hoc test to my dataset.

 Output file:

After performing the above the syntax to run, the output generated is as follows:

OLS Regression Results                                   =========================================================================================== Dep. Variable:     General_Life_satisfaction_score   R-squared:                       0.226 Model:                                         OLS   Adj. R-squared:                  0.004 Method:                              Least Squares   F-statistic:                     1.019 Date:                             Mon, 29 Oct 2018   Prob (F-statistic):              0.431 Time:                                     18:20:29   Log-Likelihood:                -27.549 No. Observations:                               19   AIC:                             65.10 Df Residuals:                                   14   BIC:                             69.82 Df Model:                                        4                                         Covariance Type:                         nonrobust                                         ======================================================================================                         coef    std err          t      P>|t|      [0.025      0.975] -------------------------------------------------------------------------------------- Intercept              7.0000      0.850      8.238      0.000       5.178       8.822 C(Ethinicity)[T.2] -2.665e-15      1.005  -2.65e-15      1.000      -2.156       2.156 C(Ethinicity)[T.3]    -1.2000      1.005     -1.194      0.252      -3.356       0.956 C(Ethinicity)[T.4]     0.2500      1.041      0.240      0.814      -1.982       2.482 C(Ethinicity)[T.5]    -0.3333      1.097     -0.304      0.766      -2.686       2.019 ============================================================================== Omnibus:                        0.874   Durbin-Watson:                   1.033 Prob(Omnibus):                  0.646   Jarque-Bera (JB):                0.824 Skew:                           0.421   Prob(JB):                        0.662 Kurtosis:                       2.423   Cond. No.                         7.89 ==============================================================================

Warnings: [1] Standard Errors assume that the covariance matrix of the errors is correctly specified. Multiple Comparison of Means - Tukey HSD,FWER=0.05 ============================================ group1 group2 meandiff  lower  upper  reject --------------------------------------------  1      2      0.0    -3.1333 3.1333 False  1      3      -1.2   -4.3333 1.9333 False  1      4      0.25   -2.9932 3.4932 False   1      5    -0.3333   -3.752 3.0853 False  2      3      -1.2   -3.5685 1.1685 False  2      4      0.25   -2.2622 2.7622 False  2      5    -0.3333  -3.0683 2.4016 False  3      4      1.45   -1.0622 3.9622 False  3      5     0.8667  -1.8683 3.6016 False  4      5    -0.5833  -3.4436 2.2769 False --------------------------------------------

Interpretation:

F-statistics is 1.019 and the corresponding p-value is 0.431.

As p-value is greater than 0.05(level of significance), we accept the null hypothesis stating that the mean general life satisfaction score among all ethnic groups are same.

Firstly, I’m uploading the Python code

Python code:

Python Output file:

The output file is as shown below;

Gender distribution univariate bar graph describes the distribution of gender in our study. ( 1 - Male, 2 - Female ). This is an example for categorical univariate bar graph representation.

The second diagram denotes the age distribution of our samples, ranging between 18 years and 25 years. This graph is an example for a quantitative bar graph pictorial representation.

The following figure shows the categorical variable of Gender and quantitative variable of Gender. This is an example for bivariate bar graph representation.

The final diagram shows us the scatter plot of food and life satisfaction. This answers our research question, that food is not associated with life satisfaction.

The following picture shows the same diagram with the fitted line.

Final Interpretation:

0I hypothesized whether food has an impact on Life?. For that, I measured food satisfaction score and life satisfaction score, gender, and their age.

I did data management to my data as required.

My Python code:

My output file:

Counts for gender modified:

5          10

6           10

5 - Male, 6 - Female

Percentages for gender modified:

5           0.50

6           0.50

5 - Male, 6 - Female

Percentages for People with greater than 20:

1   0.300000 2   0.700000

Counts for Age with set 25 to NAN:

nan          2 24            4 22            1 23            3 18            1 19            1 20            1 21            6 22            1

Explanation: