Babban matsalar da ke da alaƙa da lambobin ƙididdiga masu mahimmanci a cikin Python shine cewa yana iya zama da wahala a fahimta da fassara sakamakon. Python harshe ne mai ƙarfi, amma yana iya zama da wahala a karanta da fahimtar lambar da aka yi amfani da ita don ƙididdige ƙididdiga. Bugu da ƙari, akwai fakiti daban-daban da yawa don ƙididdige ƙididdiga a cikin Python, wanda zai iya yin wahala a zaɓi wanda ya dace don takamaiman bincike. A ƙarshe, wasu daga cikin waɗannan fakitin ƙila ba za su kasance na zamani ba ko abin dogaro kamar sauran, don haka yana da mahimmanci a yi bincike kafin amfani da su.
1. Chi-Square Test of Independence: from scipy.stats import chi2_contingency chi2, p, dof, expected = chi2_contingency(observed) 2. One-Way ANOVA: from scipy import stats F, p = stats.f_oneway(sample1, sample2, sample3) 3. Pearson’s Correlation Coefficient: from scipy.stats import pearsonr corr, _ = pearsonr(x, y)
Layin 1: Wannan layin yana shigo da aikin chi2_contingency daga ɗakin karatu na scipy.stats, sa'an nan kuma yayi amfani da shi don ƙididdige gwajin 'yancin kai na chi-square akan bayanan da aka gani. Ana adana sakamakon wannan gwajin a cikin masu canji chi2, p, dof, da tsammanin.
Layin 2: Wannan layin yana shigo da aikin f_oneway daga ɗakin karatu na scipy, sannan yayi amfani da shi don ƙididdige hanyar ANOVA ta hanya ɗaya akan samfurori uku (samfurin1, samfurin2, samfurin3). Ana adana sakamakon wannan gwajin a cikin masu canji F da p.
Layi 3: Wannan layin yana shigo da aikin pearsonr daga ɗakin karatu na scipy.stats, sannan yayi amfani da shi don ƙididdige ma'aunin daidaitawar Pearson tsakanin masu canji biyu (x da y). Ana adana sakamakon wannan gwajin a cikin masu canji corr da _.
Menene ƙididdigar ƙididdiga
Ƙididdiga masu ƙididdigewa wani reshe ne na ƙididdiga waɗanda ke amfani da bayanai daga samfuri don yin nassosi ko taƙaitawa game da yawan jama'a. Ya ƙunshi zana ƙarshe game da yawan jama'a bisa bayanan da aka tattara daga samfurin. A cikin Python, ana iya amfani da kididdigar ƙididdiga don yanke hukunci da yin tsinkaya ta hanyar amfani da dabaru daban-daban kamar gwajin hasashe, nazarin daidaitawa, nazarin koma baya, da ƙari. Waɗannan fasahohin suna ba mu damar zana bayanai masu ma'ana daga bayananmu kuma suna taimaka mana mu yanke shawara mafi kyau.
Nau'o'in ƙididdiga marasa mahimmanci
A cikin Python, akwai nau'ikan ƙididdiga masu mahimmanci da yawa waɗanda za a iya amfani da su don tantance bayanai. Waɗannan sun haɗa da gwajin t-t-tes, ANOVA, gwaje-gwajen chi-square, gwaje-gwajen daidaitawa, da kuma nazarin koma baya. Ana amfani da gwajin T don kwatanta hanyoyin ƙungiyoyi biyu ko fiye na bayanai. Ana amfani da ANOVA don kwatanta hanyoyin ƙungiyoyin bayanai da yawa. Ana amfani da gwaje-gwajen Chi-square don gwada alaƙa tsakanin masu canji na musamman. Gwaje-gwajen alaƙa suna auna ƙarfi da alkiblar alaƙar mizani tsakanin masu canji biyu. A ƙarshe, ana amfani da bincike na regression don hango ko hasashen mai dogara daga ɗaya ko fiye masu canji masu zaman kansu.
Yaya kuke rubuta kididdigar ƙididdiga
Ƙididdiga mai ƙididdigewa wani reshe ne na ƙididdiga wanda ke amfani da bayanai daga samfurin don yin ra'ayi game da yawan mutanen da aka ɗauko samfurin. A Python, ana iya yin kididdigar ƙididdiga ta amfani da ɗakunan karatu daban-daban kamar SciPy, StatsModels, da NumPy.
Don yin ƙididdiga marasa mahimmanci a cikin Python, kuna buƙatar fara shigo da dakunan karatu masu mahimmanci sannan ku yi amfani da ayyuka kamar ma'ana (), matsakaici (), yanayin (), bambance-bambancen (), daidaitaccen karkata (), t-test(), chi Gwajin murabba'i () da sauransu. Misali, idan kuna son ƙididdige ma'anar bayanan da aka bayar, zaku iya amfani da ma'anar () aikin daga NumPy:
shigo da numpy as np
bayanai = [1,2,3,4]
mean_value = np.ma'ana (bayanai)
bugawa (ma'anar_darajar) # Fitarwa: 2.5
